nervous - Story 92433 | Emotion Vectors in Gemma4-31B

The stage lights seemed to bore into Clara’s skin as she stood backstage. Her breath hitched. The host was introducing “The Queen Bee Brownies,” the signature dessert of celebrity chef, Jean-Pierre Dubois, who claimed to have invented them. Her stomach clenched. It was her mother’s recipe. A recipe she'd shared with Jean-Pierre years ago when he was a struggling chef in need of help.

She clutched her script, her knuckles turning white. The words swam before her eyes. Jean-Pierre was now a culinary icon, famous for the very creation she'd poured her heart into. She felt a tremor in her hands.

The sound of the audience's applause and her cue sent a jolt down her spine. The smile she forced felt brittle and unnatural.

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