An highly-wearable (wireless, few–channels and dry electrodes) device is proposed for EEG based valence emotion recognition. The component is a part of an instrument for real time engagement assessment in rehabilitation 4.0. The frontal, central, and occipital asymmetry were used as well known features related to emotional valence. The device was metrologically characterized on human subjects emotionally elicited through passive viewing of pictures taken from Oasis data set. As metrological references, a standardized test, the Self Assessment Manikin, was exploited. A 2nd order polynomial kernel-based Support Vector Machine reached 83.2 � 0.3% accuracy in classifying emotional valence from each 2-s epoch of EEG acquired signals.