โ€œWell, this is just great,โ€ I mumbled under my breath, my voice barely audible. I ran a hand through my hair, a nervous gesture Iโ€™d perfected over the years. My stomach had been twisting since I walked into the building this morning. I had been ignoring the rumors. I tried to focus on my emails, but the words swam before my eyes. The new VP from corporate had been making the rounds, looking grim.

I kept fidgeting. A strange tightness had wrapped around my chest, constricting my breath. Then the official announcement: The company was sold. I had known it was coming, but I still flinched at the word.

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
๐Ÿ˜ฐ0.191
๋А๊ปด0.183
๐Ÿ˜ฃ0.183
๐Ÿ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198