Electromyographic (EMG) signals provide valuable insights into muscle activity and can be leveraged for human motion classification, particularly in applications such as prosthetics, rehabilitation, and human–computer interaction. This study presents a deep learning-based approach for classifying forearm motions using EMG signals recorded from eight muscles. The dataset, comprising 30 subjects performing seven distinct motions, was preprocessed by applying a bandpass filter (10–400 Hz), down sampling to 1000 Hz, and removing unnecessary rest periods. The signals were segmented using region-of-interest (ROI) masking, ensuring precise alignment between EMG signals and motion labels. A convolutional neural network (CNN) was designed for sequence-to-sequence classification, incorporating 1D convolutional layers, transposed convolutional layers, and layer normalization techniques to effectively extract spatial patterns from the EMG data. The model was trained using the Adam optimizer with a learning rate of 0.001, mini-batch size of 32, and 100 epochs. Training and testing data were split in an 80–20% subject-independent manner, ensuring robust generalization. The trained model achieved an overall classification accuracy of 86%, with a precision of 86.00%, recall of 86.10%, and F1-score of 85.97%. The confusion matrix analysis revealed high classification accuracy for Wrist Flexion (88.4%) and Wrist Extension (87.0%), with minor misclassifications between Hand Open and Wrist Extension (12.5%) due to overlapping muscle activation. These results demonstrate the effectiveness of CNN-based models in EMG signal classification and highlight the potential for further optimization through sensor fusion, transfer learning, and advanced temporal modeling techniques. This study contributes to the field of biomedical signal processing and AI-driven motion classification, paving the way for more accurate and real-time EMG-based control systems.