The shared bathroom at the office felt claustrophobic. He’d seen Michael’s resume on the recruiter’s desk, and the similarities were uncanny. He kept checking over his shoulder, as if someone was behind him, ready to steal his chance. He felt a throbbing in his temples.

He found himself avoiding Michael in the hallways. A friendly greeting felt like a trap, a calculated attempt to gain information. At lunch, he sat at the furthest table from Michael, scanning the room, trying to guess at what he was thinking.

He started to interpret everyday gestures as clues. A casual laugh in the break room? Mocking. A thoughtful silence? Planning. He was convinced Michael was trying to undermine him, to ruin any chance he had. He barely ate, his stomach churning, his mind racing.

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