Abstract: Emotion recognition in conversation (ERC) has attracted much attention due to its wide applications. While consistent improvement is being made in this area, inevitable challenge comes from the dataset. The ERC dataset exhibits significantly imbalanced emotion distribution. While the utterances with neutral emotion predominate the data, this emotion label is always treated the same as other emotion labels in current approaches. To address the problem caused by the dataset, we propose a supervised contrastive learning specifically oriented for ERC task. We employ a novel data augmentation method emulating the emotion dynamics in a conversation and formulate supervised contrastive learning method tailored for ERC addressing the predominance and the ambiguity of neutral emotion. Experimental results on four benchmark datasets demonstrate the effectiveness of our approach.