A nice part of the review article you mentioned:

Self-modeling occurs in a suitable virtual machine when the machine develops concepts for categorizing and labeling its own states as sensed by internal monitors. In this context, qualia are defined to be what virtual machines ‘‘refer to when referring to the objects of internal self observation’’ (Sloman & Chrisley, 2003).

And the referenced Molyneux paper's abstract

I show how a robot with what looks like a hard problem of consciousness might emerge from the earnest attempt to make a robot that is smart and self-reflective. This problem arises independently of any assumption to the effect that the robot is conscious, but deserves to be thought of as related to the human problem in virtue of the fact that (1) the problem is one the robot encounters when it tries to naturalistically reduce its own subjective states (2) it seems incredibly difficult from the robot’s own naturalist perspective and, most importantly, (3) it invites the robot to engage in the exact same metaphysical responses as humans offer to the problem of consciousness. Despite the fact that it invites the robot to consider extravagant metaphysical solutions, the problem I explore is purely algorithmic.

reminds me of the Jenann Ismael book I mentioned in my comment.

Not quite books, but knowledge on philosophy of mind