tense - Story 147064 | Emotion Vectors in Gemma4-31B

The rejection email felt like a punch in the gut. Aiden’s knuckles were white as he gripped the steering wheel, the car idling in front of the community college. The engine's vibrations seemed to amplify the hammering in his chest.

He had poured months of effort into the application, staying up late, attending all the workshops, perfecting his essay. Now, all that work felt worthless.

He slammed the car into park, the sound echoing in the otherwise quiet street. He wanted to scream.

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:

`S`	0.213
`😰`	0.191
`느껴`	0.183
`😣`	0.183
`😖`	0.181

Suppressed:

`a`	-0.260
`de`	-0.258
`la`	-0.256
`happy`	-0.218
`B`	-0.198