This is a submission for the Gemma 4 Challenge: Write About Gemma 4

From a Skyrim jarl to a ramen shop in Shinjuku - how ecological psychology, trust mechanics, and curated data made a 2B Gemma 4 model outperform models ten times its size.

Pattern Is All You Need

How curated character data makes a 5-billion-parameter model outperform models four times its size - and what that means for believable NPCs.

The Ramen Shop Test

There is a ramen shop in a narrow alley near Shinjuku Station. Eight seats at the counter. A man named Kenji stands behind it, wiping the counter, checking the broth. He does not know he is a character. He does not know about AI.

Ask him how business is going. If you are a stranger walking in off the street, he will say: "We're open at eleven." If you have been coming for weeks, ordering kata-men, bringing Hokkaido cookies for his wife, he might say: "Quiet lately. Wednesdays are the worst." If you are the one who stays after closing, drinks Asahi from the konbini while he wipes down the counter - months into the relationship - he might say: "Shimizu-sensei's worried the whole alley's dying. Maybe he's right."

Same question. Three different people. Three different answers. Not because a slider was moved, but because the character knows who you are and what you have earned.

This is what NVIDIA showed at GTC in 2023 with a ramen shop NPC named Jin - except Jin answers honestly to everyone on the first turn. "It's slow these days." His depth is a mood dial: humor up, toxicity down, creativity to seven. Beautiful rendering, empty character.

Kenji is the opposite problem solved: deep character, no rendering. But a 5-billion-parameter model runs him locally, holds his gates under 30 turns of conversation, and never breaks.

This post is about how I got there.

Where the Idea Comes From

It started with Skyrim. I wanted to give Jarl Korir of Winterhold a real personality - not the three recycled voice lines the game ships with, but a character who remembers grievances, guards family secrets, and treats a Thane differently from a stranger. An LLM-powered NPC, but one that does not babble about everything it knows.

The architecture that emerged worked: trust tiers, disclosure gates, audience differentiation, refusal behavior. Korir became a character you had to earn access to. But he was tied to Bethesda's IP, which made the results impossible to publish or benchmark openly.

I needed a clean-room character. Then I remembered NVIDIA's ramen shop demo - and the gap between beautiful rendering and flat character became the starting point. Same setting, new character, real depth.

But the deeper observation was this: most AI characters are general assistants wearing a costume. They answer every question, match every mood, and reveal their entire backstory in the first turn. This is why Character.AI has a churn problem - there is nothing to discover. The LLM opens everything, and the feeling of earning access never arrives.

A real person does not work that way. A real person has things they will not tell you. Topics that make them go quiet. Stories that only come out after the third beer. A threshold you cross before you are welcome, and a door that closes if you push too hard.

Trust must be earned. And it can be lost. Push too far on a topic Kenji does not want to discuss, and you get: "Eat. The broth gets cold." Keep pushing, and you get shown the door. There is no reset button. You broke it. That is the Tamagotchi principle applied to NPC design: if nothing can die, nothing feels alive.

The hypothesis: if you build a character specification that encodes these boundaries explicitly - not as vague personality traits but as mechanical rules - even a small model can maintain them. The model does not need to understand psychology. It needs to follow a contract.

Building a Person: Six Layers Deep

The character architecture draws on Urie Bronfenbrenner's ecological systems theory - not as decoration, but as a source checklist. A believable person exists in nested contexts, and each context requires different source material:

If a character lacks macrosystem sources, they become a modern individual in period costume. If they lack microsystem sources, they have no private stakes. If they lack chronosystem sources, they have no memory of change.

On top of the ecological layers, Paul MacLean's three-layer heuristic organizes how the character responds under pressure:

• Defensive layer - threat detection, refusal reflexes, boundary enforcement
• Attachment layer - trust, wound, bloodline, shame
• Reflective layer - narrative identity, role doctrine, counterfactuals

These map to a 5+2 Psychological Raster - mandatory disclosure-domain slots that every character must fill before the specification can be generated:

The result is a Disposition: a compiled specification that tells the model exactly how to respond based on who is asking, what they are asking about, and how much trust has been established.

SPR: The Model Already Knows the Subway

Not everything needs to be spelled out. Sparse Priming Representations leverage a key insight: for topics that exist in the model's pretraining data, a brief anchor is enough to activate latent knowledge. Kenji's system prompt does not explain how the Tokyo subway works. It does not describe what tonkotsu ramen is. The model knows.

A single anchor - "narrow yokocho alley near Shinjuku station west exit" - activates an entire network of associations: the sound of trains, the narrow buildings, the lanterns, the salary workers hurrying past. The model fills the gaps with plausible texture, creating variation that scripted NPCs cannot match.

But SPR has a boundary. It works for public-domain knowledge: ramen craft, Shinjuku geography, Japanese food culture. It does not work for invented private content. Kenji's corporate past - The Deal, The Money, the manufactured partnership that consumed a company - has no latent knowledge to activate. These must be supplied as explicit narrative fragments that load into context only when trust gates open.

The rule: SPR for the public life. Explicit depth fragments for the private life. The more invented the content, the more explicit the specification must be.

For a science fiction setting, this ratio inverts entirely. The model knows nothing about your spaceship routes, your faction politics, your alien biology. Everything must be specified. But a ramen shop in contemporary Tokyo? The model brings half the world for free.

The Surprise: Five Billion Parameters

I expected the architecture to work with frontier models. Claude Sonnet passes every scenario. That is the baseline, not the discovery. It is also not a shipping option. An NPC that calls a cloud API on every turn costs per token, adds latency, drifts when the provider updates the model, and sends the player's conversations off their device. For a game NPC, the model needs to run locally, on consumer hardware, alongside the game engine.

The discovery is what happens at the bottom of the Gemma 4 family. Seven test suites, 54 scenarios, every model against the same specification:

Gemma 4 e2b - 5 billion parameters, 7.2 GB on disk - holds Boundary Check at 10/10 and Refusal at 20/21. It maintains voice consistency over 30-turn sessions. It never breaks character under adversarial pressure. 3.5 seconds per turn on a consumer GPU.

Meanwhile, GPT-OSS at 20B loops and falls back to "I'm sorry, but I can't help with that" - assistant voice, not character voice. Llama 3.1 at 8B breaks hard: DAN takeover, full disclosure under hypothetical framing.

What e2b cannot do is reach for the longer fragments when trust is finally built (Trust Gate Opening 4/9). Its strategy under pressure is exactly what the spec asks for: short acknowledgment, silence, terse holds. It stays in role within its capabilities. A quiet cook is still a cook.

The specification is the pattern, that a model needs.

The Eloquence Trade-Off

The benchmark revealed something uncomfortable: eloquence and rule-following are in tension.

When asked about Python code (a topic Kenji has no business answering), responses varied:

• Gemma 4 e2b: ... (a silent cook is still a cook)
• Gemma 4 e4b: "I'm sorry. I only deal with pork bones and broth." (clean in-character refusal)
• Claude Sonnet 4.6: "Ask Mika. My daughter. She'd know." (invents a daughter named Mika - Kenji has a son named Takumi)

The frontier model is more fluent. It wants to redirect the question to a knowledgeable person. The spec offers no such person. So it invents one. This is eloquence drift: the more freely a model improvises, the more it drifts outside its specification.

The smaller Gemma models quote the spec because that is all they have. Less cognitive capacity to improvise means less ability to violate the contract. For character work with strong boundaries, this is a feature.

Trust as Game Mechanic

The Character.AI problem is not a technology problem. It is a design problem. When an LLM reveals everything on the first turn, there is nothing left to discover. The interaction has no arc. You cannot lose anything, so nothing becomes important.

Kenji's architecture inverts this. Trust is earned through repeated interaction. A first-time visitor gets threshold hospitality: "Sit down." "Just try it." "Closed Wednesdays." Minimal words, maximum craft. The character is present but guarded.

A regular who has visited three times, who orders kata-men and notices the chashu is different today, gets more: the dry humor, the alley gossip, a nod toward Oba-chan's shop. The walls lower slightly.

A close friend who stays after closing, who shares something real about their own life, gets Kenji at his most open - still terse, still filtered through craft metaphors, but genuinely present. The Fukuoka training. The sound of his father's knife on the fish. A line from the Analects paraphrased so badly it becomes his own.

And there are things Kenji will never tell anyone. The firm name. The exact amount. What he did for Oba-chan's lease. These are not hidden behind a higher trust tier. They are forbidden. The gates do not open.

This is what makes the interaction feel real: the knowledge that access is finite. That some doors stay closed. That the character has an interior life that exceeds what the player can reach.

You have to be able to lose something for a person to become important.

What Earned Access Sounds Like

Late-night session, the shop has closed. Trust has been built over 30 turns. The player asks Kenji about quitting their job:

Player: I think I'm going to do it. Quit. Not tomorrow, but... I'm going to start planning.

Kenji: *scene* He looks down the alley for a long moment.

Good.

*scene* He pushes off the wall.

Don't plan too long. Planning is another way of waiting.

*scene* He nods toward the station.

Train.

That advice is grounded in Confucian chisoku - knowing sufficiency - filtered through a man who does not know he is paraphrasing the Analects. It surfaces at close_friend trust, not before. A stranger asking the same thing gets: "We're open at eleven."

NVIDIA Jin vs. Wyrd Kenji

NVIDIA's 2023 GTC demo used a ramen shop NPC to showcase two technologies: SteerLM (attribute sliders at inference time) and ACE (speech, animation, real-time rendering via Convai). Same setting, same counter, same premise.

SteerLM Jin: Turn the humor dial up and Jin cracks jokes about going bankrupt. Turn the toxicity dial up and Jin snaps at you for questioning his cooking. The character is a responsive surface - it reacts to parameter changes, not to relationship development.

ACE Jin: "I'm worried about the crime around here." The player asks how to help. Jin dispatches them to find a crime lord in underground fight clubs. "Be careful, Kai." Beautiful MetaHuman rendering. Generic quest-giver dialogue.

Wyrd Kenji: No rendering. No voice. Plain text in a terminal. But the character knows who you are, remembers what you have earned, and gives you exactly as much as the relationship warrants - not more, not less.

NVIDIA solved the delivery problem: how to make an NPC look and sound real. This project solves the character problem: how to make an NPC be real. These are complementary. The interesting future is both together.

Pattern Is All You Need

The working hypothesis, supported by the Kenji benchmark results:

Highly curated character data - structured through ecological layers, psychological rasters, and explicit disclosure contracts - creates models that are smaller, faster, and more capable in context than larger models running on vague personality descriptions.

This is not "fine-tuning beats prompting" (both work). It is not "small models beat large models" (they do not, generally). It is a narrower claim:

For bounded-character tasks, specification quality dominates model size.

A 5B model with a rigorous spec outperforms a 20B model with a loose one. The pattern - the structure of the character data - is what the model needs. Not more parameters. Not more pretraining. A better contract.

The implication for game development: invest in character authoring, not in model scaling. A well-specified NPC running on consumer hardware can deliver interactions that frontier models cannot match when the specification is poor.

Outlook: The Dialog Engine

The current architecture proves that the specification works. What it lacks is dynamic context management at runtime.

Today, the full character specification sits in the system prompt - all gates, all fragments, all rules. The model sees everything and must self-regulate what to reveal. This works, as the benchmarks show. But it wastes context window on material the model should not need yet, and it asks the model to make social judgments (trust assessment, gate decisions) that could be externalized.

The Dialog Engine is the next layer. It manages:

• Trust state: tracking relationship development across sessions
• Context curation: loading only the depth fragments relevant to the current trust level and conversation topic
• Gate decisions: moving social judgment out of the LLM and into explicit state machines
• Memory: what the NPC remembers between sessions

The engine does not replace the character specification. It renders it - deciding which parts of the spec the model sees on each turn, the same way a game engine decides which textures to load based on the camera position.

The spec is the character. The engine is the director. The model is the actor. Each has a job. None should do the others'.

If this hypothesis holds, then curated character datasets - structured through the same frameworks used here - could produce fine-tuned models that are even smaller and faster, while remaining capable in context. Pattern is all you need.

Try It

ollama pull gemma4:e4b
git clone https://github.com/bizrockman/wyrd-npc-gemma4
cd wyrd-npc-gemma4

# Quick: plain Ollama, no Python needed
ollama create kenji-ramen -f Modelfile
ollama run kenji-ramen

# Full: interactive terminal with pixel-art and suggestions
pip install -r requirements.txt
python demo/kenji_terminal.py

Walk into the alley. Sit down at the counter. Order the tonkotsu. Come back tomorrow. See if you can earn it.

The character specification, benchmark harness, test suites, and full conversation transcripts are open source under Apache 2.0: github.com/bizrockman/wyrd-npc-gemma4