The flickering fluorescent lights in the office seemed to pulse with a malevolent energy, mirroring the frantic beat in Amelia's chest. Every shadow cast by the water cooler became a lurking figure, their intentions unclear. She kept glancing at the security cameras, each lens a cold, unblinking eye.

Her palms were slick, leaving damp fingerprints on the coffee mug she clutched. The aroma, usually comforting, now smelled faintly like betrayal. She caught the eye of her manager, Mr. Henderson, across the open-plan office. He gave her a tight, almost imperceptible smile. It didn’t feel friendly.

Amelia's breath hitched as she returned to her computer, the quiet hum of the server room suddenly sounding like the nervous chittering of mice. She replayed conversations in her head, searching for clues, for whispers of impending doom. Did she miss something? Were people behaving differently? She couldn't shake the feeling that she was being watched.

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