The fluorescent lights of the office hummed, a sound now amplified in Thomas’s ears. He kept replaying the whispered conversation he’d overheard in the breakroom. "Fifty-five grand? Seriously?" He was sure the voice belonged to Sarah, the new hire in accounting. The air felt thick, heavy with unspoken truths. His stomach churned.

He avoided Sarah's gaze when they passed in the hallway, his steps quick and furtive. Every casual interaction now felt laden with subtext. Was she looking at him with pity? With triumph?

He found himself constantly checking the time, anticipating the inevitable meeting with his supervisor. The man’s usual affable demeanor seemed forced today, like a carefully constructed facade. Thomas’s palms were slick, and he clenched his fists, trying to stop his hands from shaking.

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