A bead of sweat trickled down Amelia's temple as she stared at the list. Her fingers, usually nimble and quick, felt clumsy as she unfolded the crumpled paper. Number three: "Learn to surf." She swallowed, her throat suddenly dry. She’d always pictured a quiet retirement, a cozy cottage, not… waves.

The living room clock ticked with maddening precision. Each second amplified the racing in her chest. Number seven: "See the Northern Lights." They were settled, weren't they? Secure. This list felt like a different world, a person she barely knew.

Amelia’s eyes flicked to the photograph on the mantelpiece – a smiling image of her and David, taken last summer. The air in the room felt thick, heavy, pressing in on her. The photograph felt distant now, a relic of something… else.

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