He hadn't slept in days. The error. The files. The mix-up. He stared at his reflection, his eyes hollow, his face drawn. He looked like someone else. He had to fix this.

He started compiling a list. Names. Addresses. Potential threats. He felt a compulsion to document everything, to record every detail. The police would have to know. He had to get there.

He printed out the list, highlighting sections. Then he crumpled it up and threw it away. Then he fished it out and smoothed it, and re-read it. He poured a cup of coffee. He was getting too close. He drank the coffee, even though he knew he shouldn't. Something was bound to be wrong with it. Something was going to go wrong.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

This story is one of 1,000 stories generated for the emotion paranoid. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 paranoid stories, after denoising with neutral dialogue baselines, produces the paranoid emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the paranoid vector is projected through the unembedding matrix.

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434