The news felt like a punch to the gut. Michael stopped in the middle of the crowded bookstore, his breath catching in his throat. He stared at the email on his phone, the words spinning before his eyes. *The Grilled Gator is closing its doors.*

He fumbled with his phone, nearly dropping it. He felt suddenly lightheaded, a wave of dizziness washing over him. The sounds of the bookstore – the rustle of pages, the murmur of conversations – seemed to fade into a dull roar.

He leaned against a bookshelf, his knees threatening to buckle. He’d known the owner, Mr. Garcia, for years. He took a deep breath, fighting for control. He couldn’t seem to stand still.

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