The university’s website, the very platform where his words were now displayed, became a source of constant dread. He found himself obsessively checking the page views, the comments, the reaction metrics. The numbers seemed to mock him, each one a tally of his vulnerability. He’d deleted his social media accounts, but the internet seemed to be everywhere, a constant surveillance. He started to feel like the target of a hidden camera, watched by an unseen audience. He spent hours trying to find flaws, tiny errors, anything to explain what was happening.

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