The hospital room felt cold, sterile. She had been nervous. The smell of antiseptic, the rhythmic beep of the machines, the silence of the room. She stood over his bed, her hand hovering over his. He was older, of course, but the way his hair fell over his forehead, the shape of his nose, the curve of his smile, were all so familiar.

She’d finally found him after all these years. In her panic, she'd barged into his room. He’d looked at her, and she had started to speak. He had looked at her with a blank expression. He was recovering from an accident. Head trauma. She knew.

She felt a wave of dizziness wash over her. Her vision swam. It was a pressure around her temples. A dull ache. She felt the tears welling up in her eyes. It was a knot in her stomach. She bit down on her lip, attempting to regain control. She had to stay strong.

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