The subway car was a steel cage, the rhythmic screech of the train a physical assault on David's senses. He pressed himself against the window, trying to create more space between himself and the other passengers. He held his breath. He hated crowded places. His palms were slick with perspiration.

He saw a woman on the platform, hunched over, clutching her stomach. He recognized the pattern of her posture, the way she was trying to disappear into herself. He could sense her inner turmoil.

As they both stepped off the train, the woman turned to him, her eyes bright with a mixture of fear and something else – recognition? "Excuse me," she whispered, her voice barely audible over the platform noise. "Are you… are you alright?"

David stared at her, frozen. He swallowed. He knew exactly what she meant.

"They said it was unique," she continued. "That… no one else has this."

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198