Recently, the supervised learning paradigm's surprisingly remarkable performance has garnered considerable attention from Sanskrit Computational Linguists. As a result, the Sanskrit community has put laudable efforts to build task-specific labeled data for various downstream Natural Language Processing (NLP) tasks. The primary component of these approaches comes from representations of word embeddings. Word embedding helps to transfer knowledge learned from readily available unlabelled data for improving task-specific performance in low-resource setting. Last decade, there has been much excitement in the field of digitization of Sanskrit. To effectively use such readily available resources, it is very much essential to perform a systematic study on word embedding approaches for the Sanskrit language. In this work, we investigate the effectiveness of word embeddings. We classify word embeddings in broad categories to facilitate systematic experimentation and evaluate them on four intrinsic tasks. We investigate the efficacy of embeddings approaches (originally proposed for languages other than Sanskrit) for Sanskrit along with various challenges posed by language.