The field of computational intelligence has mostly overlooked the classification of emotional states from poetry or formal text in recent times, unlike informal textual content such as SMS, email, chat and online reviews. To fill this gap, a new study proposes an emotional state classification system for poetry text that utilizes Deep Learning technology. Specifically, the study intends to use an attention-based C-LSTM model to categorize poetry text into various emotional states, including love, joy, hope, sadness, and anger.