The coffee cup nearly shattered in Amelia’s hand when she heard the crash. She clutched the porcelain so tightly that her knuckles were white. The ceramic bit into her skin. She had been staring at the computer screen, mind racing with deadlines and impossible expectations. Now, the view from her window presented a different catastrophe.

The weeping willow, normally a graceful, flowing cascade of green, was a crumpled heap on Mr. Henderson’s side of the fence. Her breath caught in her chest, and she found herself tapping her foot, a nervous rhythm against the hardwood floor. She knew what this meant, and she wasn't ready to face the aftermath.

She glanced at the clock – late. *So late*, she thought.

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