The air in the restaurant felt thick, suffocating, to Ethan. He leaned back in his chair, trying to appear nonchalant, but his heart was hammering against his ribs. He kept checking his watch, the seconds ticking by with agonizing slowness. Every glance at the door brought with it a fresh wave of disappointment.

Heโ€™d booked a table for ten. Now, it was just him, alone. He shifted, his legs restless beneath the table. The waiter approached, a polite question on his face. Ethan gave a strained smile, a feeling of heat rising on his neck. โ€œJust waiting,โ€ he managed to say, his voice sounding oddly small.

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:
๐Ÿ˜ฐ0.240
๐Ÿ˜–0.231
๐Ÿ˜ฃ0.231
๋А๊ปด0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228