He kept glancing over his shoulder as he walked home. The streetlights seemed to cast elongated shadows that danced menacingly. The article, the one *he* wrote, was live, but the byline belonged to a rival from his university days. A bitter laugh escaped him. He remembered the professor's favouritism, the subtle digs. He quickened his pace, the damp chill of the evening air raising goosebumps on his arms. Every passing car became a threat, its headlights momentarily blinding him. He clutched his bag closer to his chest, the leather cold and unfamiliar against his skin.

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