The research focuses on developing an electroencephalography (EEG) based emotion recognition system to identify happy, neutral, and negative emotions. The suggested framework uses Simple Recurrent Neural Networks (SimpleRNN) networks to capture the temporal information of the EEG data. Identifying prominent EEG bands for emotion classification and the ensemble of Simple RNN based on these bands are significant contributions of this research. The proposed model achieved 83.39% on a publicly available dataset SJTU Emotion EEG Dataset (SEED). The dual-tree Complex Wavelet Transform (DT-CWT) is used to decompose the signal into five bands, and then the features are extracted from each. By drawing parallels between the capabilities of shallow, deep, and ensemble models, the authors show how their suggested emotion detection system may provide adequate identification performance at a reasonable computational cost. The results indicate that higher frequency bands of EEG signals are more effective in identifying emotions. The study contributes particularly to addressing the time-dependence trait of emotion processing. The proposed method has the potential for practical applications in various fields, such as psychology and human-computer interaction, where identifying emotional states is crucial.