nervous - Story 92313 | Emotion Vectors in Gemma4-31B

The coffee mug rattled slightly in Marco's grasp as he stared at the sticky note stuck to the refrigerator. He’d found it this morning, a hastily scrawled message in Italian. His Italian, the language he hadn’t thought about in years, the language he’d always considered a private corner of his world.

He ran a hand through his hair, a faint tremor running through him. The words were simple, a shopping list, but the implications were huge. He glanced around the apartment, his usual easygoing gaze sharper than usual. The air felt charged with something he couldn't quite define.

Later, he found Maria in the living room, a language learning app open on her laptop. Her face was a study in concentration, a slight furrow in her brow.

Emotion: nervous

Cluster: Fear / Anxiety

PC1 (Valence): -1.08 Negative

PC2 (Disposition): -0.47

Role in Research

This story is one of 1,000 stories generated for the emotion nervous. 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 nervous stories, after denoising with neutral dialogue baselines, produces the nervous emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the nervous vector is projected through the unembedding matrix.

Promoted:

`worse`	0.229
`trem`	0.203
`😰`	0.203
`😨`	0.201
`緊張`	0.200

Suppressed:

`la`	-0.397
`que`	-0.260
`a`	-0.242
`B`	-0.217
`H`	-0.210