The taste of coffee was metallic on Mark's tongue, a bitter echo of the unsettling conversation with David earlier. They were discussing the car accident. Mark remembered the screech of tires, the sudden impact. David’s account was different. Almost completely different.

He felt a tremor run through him, starting at his fingertips. He gripped the mug tighter, knuckles turning white. The gentle hum of the refrigerator seemed menacing. The familiar sounds of his own home had transformed into something sinister. He checked the locks on the doors again.

The details of the accident swirled in his mind, confusing him. The light, the angle, the color of the other car. David's version felt like a deliberate contrivance. He felt the cold pressure on his chest intensify, a physical manifestation of his disquiet.

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