The train rumbled along the tracks, the rhythmic clatter of the wheels a jarring counterpoint to the quiet desperation building inside him. He’d seen her, Lily, after ten years. Her cold denial, the vacant expression on her face, had been enough to shatter him. He pressed his face against the cold glass of the window.

He felt the weight of his own memories, the shared laughter, the whispered secrets, and the overwhelming feeling of betrayal. He felt the urge to jump. He felt the hot tears on his cheeks and the chill of the evening air seep into his skin. He felt the train was taking him somewhere bad. He felt entirely alone.

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