Recognition of emotions from human plays a vital role in our day to day life and is essential for social communication. Automatic emotion recognition is becoming recent research focus on artificial intelligence. A facet of human intelligence is the ability to recognize emotion that is regarded as one of the attribute of emotional intelligence. Although research based on facial expressions or speech is seen in thrive, recognizing emotions from body gestures remains a less explored topic. This chapter proposes a machine learning approach and discussed with deep learning model to achieve emotional intelligence. The block based intensity value (BBIV) feature and the different bin level HoG feature (DBLHoG) are extracted from human body movements and are fed to a supervised learning algorithm. Support vector machine (SVM), k-nearest neighbor (KNN) and random forest classifiers are the supervised learning algorithm used in this chapter. Finally, the pre-trained deep convolutional neural network (DCNN) model is used. The experiment is conducted using Geneva multimodal emotion portrayals (GEMEP) corpus dataset. In this dataset, human body movement expressing the five archetypical emotions likes (anger, fear, joy, pride and sad). In this emotions recognition system, The random forest classifier outperformed better than the SVM and kNN classifier. Finally DCNN model achieve better recognition than random forest classifier. This chapter gives a brief study on achieving emotional intelligence with a DCNN Model.