In this paper, we present an emotion recognition methodology that utilizes information extracted from body motion analysis to assess affective state during gameplay scenarios. A set of kinematic and geometrical features are extracted from joint-oriented skeleton tracking and are fed to a deep learn-ing network classifier. In order to evaluate the performance of our methodolo-gy, we created a dataset with Microsoft Kinect recordings of body motions ex-pressing the five basic emotions (anger, happiness, fear, sadness and surprise) which are likely to appear in a gameplay scenario. In this five emotions recog-nition problem, our methodology outperformed all other classifiers, achieving an overall recognition rate of 93%. Furthermore, we conducted a second series of experiments to perform a qualitative analysis of the features and assess the descriptive power of different groups of features.