“Another?” the waiter asked, his voice a little too loud. Renata had downed three glasses of wine and barely touched her plate of pasta. The review, vicious and personal, sat in her mind like a festering wound. She felt a throbbing in her temples.

She waved the waiter away. She couldn't focus. Each bite of food felt like a challenge, a dare to disagree with the critic's harsh pronouncements. She pushed the pasta around her plate, the sauce smearing like a bad memory.

She excused herself from the table and went to the bathroom. She stared at her reflection, her eyes wide and haunted. Was she a failure? Had she deluded herself for so long?

She ran the water in the sink. She splashed her face. It didn’t help.

Emotion: uneasy

Cluster: Fear / Anxiety
PC1 (Valence): -1.80 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.240
😖0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228