For a coincidence two hours ago I posted a video on my channel where it can be seen how king-man+woman also works with CLIP image embeddings. This may be obvious for people that worked with CLIP extensively, or that tried embeddings math in other embedding spaces, but it really surprised me.
https://youtu.be/r6TJfGUhv6s?si=wG6h1kdigiPrNFdk
Video is in English but please pardon my and my friend Italian accents...