The silence in the apartment was deafening, the echo of the argument still ringing in my ears. I needed to focus, to write, to escape into the world of my book. But my heart was racing, a trapped bird fluttering in my chest.

Then, the scrape of nails on the fence. I took a deep breath, trying to calm the racing thoughts.

Buster. Again. This time, he was tearing through the hydrangeas. I stood frozen for a moment, then moved like a sleepwalker to the back door, my movements jerky and uncoordinated.

"Buster, no!" My shout felt forced and thin, swallowed by the late afternoon.

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