The success of live comedy depends on a performer's ability to 'work' an audience. Ethnographic studies suggest that this involves the co-ordinated use of subtle social signals such as body orientation, gesture, gaze by both performers and audience members. Robots provide a unique opportunity to test the effects of these signals experimentally. Using a life-size humanoid robot, programmed to perform a stand-up comedy routine, we manipulated the robot's patterns of gesture and gaze and examined their effects on the real-time responses of a live audience. The strength and type of responses were captured using SHOREtm computer vision analytics. The results highlight the complex, reciprocal social dynamics of performer and audience behavior. People respond more positively when the robot looks at them, negatively when it looks away and that different performative gestures elicit systematically different patterns of audience response. This demonstrates that the responses of individual audience members depend on the specific interaction they're having with the performer. This work provides insights into how to design more effective, more socially engaging, forms of robot interaction that can be used in a variety of service contexts.