Emotions are a natural vector for acting together with others and are witnessed in human behaviour, perception and body functions. For this reason, studies of human-to-human interaction, such as multi-person motor synchronisation, are a perfect setting to disentangle the linkage of emotion with socio-motor interaction. And yet, the majority of joint action studies aiming at understanding the impact of emotions on multi-person performance resort to enacted emotions, the ones that are emulated based on the previous experience of such emotions, and almost exclusively focus on dyadic interaction. In addition, tasks chosen to study emotion in joint action are frequently characterised by a reduced number of physical dimensions to gain experimental control and subsequent facilitation in data analysis. Therefore, it is not clear how naturalistically induced emotions diffuse in more ecological interactions with other people and how emotions affect the process of interpersonal synchronisation. Here, we show that positive and negative emotions differently alter spontaneous human synchronous behaviour during a multi-person improvisation task. The study involved 39 participants organised in triads who self-reported liking improvisational activities (e.g., dancing). The task involved producing improvisational movements with the right hand. Participants were emotionally induced by manipulated social feedback involving a personal ranking score. Three-dimensional spatio-temporal data and cardiac activity were extracted and transformed into oscillatory signals (phases) to compute behavioural and physiological synchrony. Our results demonstrate that individuals induced with positive emotions, as opposed to negative emotions or a neutral state, maintained behavioural synchrony with other group members for a longer period of time. These findings contribute to the emerging shift of neuroscience of emotion and affective sciences towards the environment of social significance where emotions appear the most—in interaction with others. Our study showcases a method of quantification of synchrony in an improvisational and interactive task based on a well-established Kuramoto model.