Spontaneous multi-party interaction - conversation among groups of three or more participants - is part of daily life. While automated modeling of such interactions has received increased attention in ubiquitous computing research, there is little applied research on the organization of this highly dynamic and spontaneous sociable interaction within small groups. We report here on an applied conversation analytic study of small-group sociable talk, emphasizing structural and temporal aspects that can inform computational models. In particular, we examine the mechanics of multiple simultaneous conversational floors - how participants initiate a new floor amidst an on-going floor, and how they subsequently show their affiliation with one floor over another. We also discuss the implications of these findings for the design of "smart" multi-party applications.