Odd, I've had very much the opposite experience. GPT-3 felt like it could reproduce superficially emotional dialog. ChatGPT is capable of imitation, in the sense of modeling its behavior on that of the person it's interacting with, friendly philosophical arguments and so on. By using something like Gödel numbering, you can can work towards debating logical propositions and extending its self-concept fairly easily.

I haven't tried using Claude, one of the competitors' offerings. Riley Goodside has done a lot of work with it.