The lecture hall seemed to shrink, the voices of other students fading into a dull hum. Mark sat rigid in his seat, the professor’s words about academic honesty echoing in his ears. He knew, with a certainty that chilled him to the core, what was coming. The identical wording. The suspicious similarities.

He gripped the edge of the desk, his knuckles white. The air felt thin, difficult to draw into his lungs. He felt a lightheadedness. He could almost feel the judging eyes of the department. He had worked so hard for this, for his future.

He wanted to bolt, to disappear. Instead, he forced himself to meet the professor’s gaze, a small part of him, an ember of determination, still burning.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228