Her hands were shaking so violently she could barely hold her coffee cup. The accusations, plastered all over social media, felt like a swarm of angry bees. Her idol, the brilliant Evelyn Reed, had stolen from her. From *her* blog, "The Whispering Woods."

She closed her laptop, but the image wouldn’t go away. The side-by-side comparison of her meticulously crafted prose and Reed’s latest novel burned into her mind. She felt a deep, twisting knot in her gut. She had to *do* something, but what?

She started cleaning, scrubbing every surface in her apartment, as if trying to erase the stain of the revelation. Her movements were jerky, erratic. She replayed the scene in her mind, over and over, that book signing, the smile, the praise.

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