The silence in the workshop was deafening. Just last week, Sarah and her mentor, Mr. Henderson, were hunched over their workbenches, discussing the intricacies of the new prototype. Now, the space felt vast and empty. Dust motes danced in the lone ray of sunlight, mocking her unease.

She’d left a thank-you note on his desk, but it felt childish now, insignificant. She checked her phone for messages, re-reading old texts with a furrowed brow. Each tap of her foot echoed in the quiet, a percussive beat to her building anxiety.

She started checking the security cameras, replaying the footage of the last few days, searching for the moment he decided to leave. Had she said something wrong? Was she being blamed for something? The image of the camera lens seemed to bore into her, a cold, unblinking eye.

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