The gravel crunched under Amelia's boots with each step. Her jaw worked, a subtle grinding that she hadn't realized she was doing. The air in the park, usually a source of calm, felt thick and heavy today, mirroring the weight she carried inside. She clutched the faded photograph tighter, the edges worn smooth from years of handling.

There. The empty space. Where it used to be. A sick feeling churned in her stomach. It was like seeing a missing limb. The scar was fresh, raw, the wood chips scattered like forgotten tears.

"Excuse me," she croaked, her voice barely a whisper. She addressed the park attendant, a man methodically sweeping leaves. "Did... did you see who...?" Her words caught, her chest constricting as if someone had wrapped a steel band around it.

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