Activation Steering with Jungian Cognitive Functions

arXiv:2607.20803 · cs.CL, cs.AI, cs.LG · Submitted 2026-07-23 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-07-23

Updated: 2026-10-13

Comments: 16 pages, 9 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Steering — 6× in this paper · explained in 2 episodes
• Activation Steering — 4× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering
• Persona Vectors: Monitoring and Controlling Character Traits in Language Models
• From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models
• Linear Personality Probing and Steering in LLMs: A Big Five Study
• The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering