From his desk, he watched them. Everyone. His coworkers, the managers, even the office intern. He catalogued their smiles, their frowns, their glances in his direction. Each interaction was meticulously analyzed. He felt like an actor on a stage with a critical audience.

His chair creaked, a sound that seemed amplified in the quiet office. He adjusted it, and the sound echoed, drawing everyone's gaze. He felt the blood rush to his face, convinced he had been exposed. The water cooler, now, was an enemy, with its friendly gurgle.

The interview for the promotion was just two days away. He imagined the questions, the traps. He practiced his answers in the mirror, his face a mask of false confidence. Each night, he awoke in a cold sweat.

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