The ability to do approximate arithmetic on word vectors is nifty, but what I think is most interesting is that Word2vec shows that we can translate fuzzy human concepts such as english words or sentences into an encoding from which computers can extract semantic information. There are now machine translation models based on recurrent neural networks which take a sentence in a language X, generate an activation vector, and then feed that vector into another recurrent neural network trained to generate text in another language Y. Could it be that this temporary store of information is the human brain's equivalent of a CPU's register file, built out of a relatively small set of neural registers, with inhibitory neurons gating their outputs?