He slammed the newspaper down. The headline screamed about the stock market, and his stomach lurched again. It was the only warning he had before the enormous crash. The sickening sound, like a giant hand slapping the earth, had him jumping. David, even with the weight of the day, ran to the window.

His neighbor’s sprawling maple was gone, replaced by a chaotic mess of splintered wood. Its branches had consumed half of the yard and blocked off access to his shed. He felt a throbbing ache in his temples that he recognized as the precursor to a migraine. The shed held his tools, his carefully manicured garden.

“Damn it,” he muttered, balling his hands into fists. He thought of the insurance forms, the calls, the inevitable hassle. It felt so incredibly heavy.

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