cs.AISep 3, 2026

Inferring Affective Consciousness in an Artificial Agent: A Case Study

Authors: Mark SolmsSt John GrimblyBruce BassettEvert BoonstraRowan HodsonNicolas KuskeKival MahadewBenjamin Rosman+2 more

Organizations: Neuroscience Institute, University of Cape Town, South Africa. · Dept. of Psychology, University of Cape Town, South Africa. · Dept. of Mathematics & Applied Mathematics, University of Cape Town, South Africa. · School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa. · Machine Intelligence and Neural Discovery Institute, University of the Witwatersrand, Johannesburg, South Africa. · Laureate Institute for Brain Research, University of Tulsa, OK, USA. · Dept. of Cognitive Robotics, Delft University of Technology, Delft, Netherlands. · National Institute for Theoretical & Computational Sciences, Stellenbosch, South Africa. · Institut National de la recherche scientifique, Montreal, Quebec, Canada.

Abstract

Creatures that display 'hedonic place preference behaviour' are thought by many scientists to experience feelings, on the assumption that their attraction to pleasure-producing substances which lack nutritional value (e.g. cocaine, morphine) cannot easily be attributed to unconscious instinctual behaviour. In this paper, we discuss how a simple artificial agent that instantiates attributes of an affective system engaging in felt uncertainty about its intrinsic needs in relation to environmental resources can similarly display hedonic place preference behaviour -- through an apparently subjective form of information processing -- while simultaneously being entirely deter-ministic. We outline some implications of this artificially engineered behaviour for our understanding of the physical basis of consciousness and the experience of free will.

Explore similar work

CardsList