Disclosed are an emotional evolution method and terminal for a virtual avatar in educational metaverse. By collecting expression data and audio data of the virtual avatar, and performing emotional feature extraction based on the expression data and the audio data; fusing an extracted sound emotional feature with an extracted expression emotional feature by using an emotional feature fusion model, and performing emotion recognition on a multi-modal emotional feature fusion result obtained by fusion to obtain an emotional category corresponding to the multi-modal emotional feature fusion result; labeling the multi-modal emotional feature fusion result based on a semantic vector of the emotional category to generate an emotional evolution sequence; and driving the virtual avatar to perform emotional expression according to a target emotional evolution pattern extracted from the emotional evolution sequence, a unified and united multi-modal emotional feature fusion result is formed, the emotional self-evolution of the virtual avatar is achieved.