The elevator ride felt like an eternity. He had just seen the spreadsheet. He felt a throbbing pulse in his temples. Why would they do this? The faces of his colleagues seemed different, judgmental, and he felt a knot forming in his stomach.

He began avoiding the water cooler, the communal space where the whispers thrived. He was certain they were talking about him, dissecting his shortcomings, celebrating his perceived inadequacy. He could practically hear the laughter.

He started second-guessing every decision, every email. He re-read his emails over and over. He would constantly be running to the bathroom to check his face in the mirror and breathe deeply. The weight of it all was crushing.

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