The coffee tasted bitter, a reflection of the sourness brewing inside him. He’d overheard the exchange during his lunch break: "Starting salary? Quite decent, I'd say." From the intern’s mouth, words that cut like knives. His own desk felt smaller, the walls closing in.

He started avoiding the elevator, opting for the stairs, even though they were a longer walk. He would catch his own reflection in the glass doors and barely recognize himself. He looked haggard, his eyes darting around the office. He was starting to overanalyze every comment, every gesture, of the new guy.

He checked his work email obsessively, fearing he’d been excluded from crucial communications, from projects, from everything. Each ping sent a jolt of anxiety through him. He found himself imagining a secret meeting, a clandestine plot to replace him.

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