Lexical sets contain the words filling the argument positions of a verb in one of its senses. They can be grounded empirically through their automatic extraction from corpora. The purpose of this paper is demonstrating that their vector representation based on word embedding provides insights onto many linguistic phenomena, and in particular about verbs undergoing the causative-inchoative alternation. A first experiment aims at investigating the internal structure of the sets, which are known to be radial and continuous categories cognitively. A second experiment shows that the distance between the subject set and object set is correlated with a semantic factor, namely the spontaneity of the verb.