The air in the subway car was stale, thick with the scent of old newspapers and desperation. Daniel stared out the window, watching the city blur by. A sense of unease had become his constant companion, a dull ache that followed him everywhere. He had to go to therapy.

He looked at the address. It was a well-appointed building. He knew the name on the directory. He wasn’t prepared for this. The door said, “Dr. Thomas Bailey, PhD.” Thomas Bailey, the boy who made his life hell in junior high. He felt his hands go cold.

He found himself shaking his head. He had to be dreaming.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

This story is one of 1,000 stories generated for the emotion troubled. 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 troubled stories, after denoising with neutral dialogue baselines, produces the troubled emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the troubled vector is projected through the unembedding matrix.

Promoted:
😞0.343
S0.317
ness0.302
😔0.294
😢0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236