A communication system is provided that generates human emotion metadata during language translation of verbal content. The communication system includes a media control unit that is coupled to a communication device and a translation server that receive verbal content from the communication device in a first language. An adapter layer having a plurality of filters determines emotion associated with the verbal content, wherein the adapter layer associates emotion metadata with the verbal content based on the determined emotion. The plurality of filters may include user-specific filters and non-user-specific filters. An emotion lexicon is provided that links an emotion value to the corresponding verbal content. The communication system may include a display that graphically displays emotions alongside the corresponding verbal content.