The air was thick, laden with the smell of old furniture and forgotten things. His mind reeled from the meeting, the harsh words, the implied threat. His hands felt clammy. He wandered through the stalls, desperate for a distraction, for something to anchor him.

He almost missed it, tucked away in the corner. His childhood bear, Teddy. Missing an eye, its fur matted. It looked so forlorn. He felt a sharp pang ofโ€ฆ something.

He cleared his throat. "How much for the bear?" The seller, a young girl with pigtails, looked up, her expression bright.

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