The Quran is known for its linguistic and spiritual value. It comprises knowledge and topics that govern different aspects of people's life. Acquiring and encoding this knowledge is not a trivial task due to the overlapping of meanings over its documents and passages. Analysing a text like the Quran requires learning approaches that go beyond word level to achieve sentence level representation. Thus, in this work, we follow a deep learning approach: paragraph vector to learn an informative representation of Quranic Verses . We use a recent breakthrough in embeddings that maps the passages of the Quran to vector representation that preserves more semantic and syntactic information. These vectors can be used as inputs for machine learning models, and leveraged for the topic analysis. Moreover, we evaluated the derived clusters of related verses against a tagged corpus, to add more significance to our conclusions. Using the paragraph vectors model, we managed to generate a document embedding space that model and explain word distribution in the Holy Quran. The dimensions in the space represent the semantic structure in the data and ultimately help to identify main topics and concepts in the text.