Automated Emotion Recognition (AER) is the process of programmatically identifying and classifying affective responses to stimuli through the analysis of physiological signals. AER has applications in interpersonal communications via digital mediums, human-computer interactions, third-party monitoring and surveillance, personal health and wellness, and in physical and mental health treatment settings. In this paper, we demonstrate AER using deep learning for automated feature extraction from ECG signals using a novel application of temporal convolutional neural networks (TCNN) to resolve the time-dependent nature of the biomedical signal data. We achieve the classification accuracy of 98.68% for arousal and 97.37% for valence using two publicly available datasets. These results demonstrate viability of TCNN for use in advanced AER solutions, and set the stage for application of temporal CNN to a wide range of biomedical signal processing applications.