The seaside cottage was cold, damp, and smelled of salt and decay. The list, scrawled on a faded postcard, lay on the weathered coffee table. "See the whales." He traced the words with a hesitant finger. The ocean roared outside, a constant, mournful sound. He ran a hand over his face, his skin prickling with goosebumps. His father had been a man of the sea, yet he’d never seen a whale. A sudden, sharp sob escaped him. He felt as though he were trapped, like a fly buzzing helplessly in a spider's web.

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
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198