The critic's words reverberated in Leo's head, each syllable a hammer blow. He stared at the handwritten recipe for the evening's special, the familiar ink lines blurring before his eyes. His hand trembled as he reached for the salt cellar. He missed a pinch.

He kept replaying the meal in his head. Did he season the scallops enough? Was the sauce too heavy? Every detail was now a potential flaw, a potential nail in the coffin of his restaurant. He wanted to scream.

He called his wife. Her voice on the phone soothed him. He told her the review was unfair and that it was no big deal. They could get through anything. She didn't buy it. He knew she didn't buy it.

He walked into the dining area. He felt the weight of expectation with the few patrons present. He felt his face heat up when he saw the diners. It was all a disaster.

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