“Morning, Frank!” The overly cheerful greeting felt forced even to her own ears. Across the manicured lawn, she saw David, the seemingly ordinary IT guy, loading what looked like designer luggage into a helicopter. A helicopter! Her grip tightened on her morning coffee cup. She'd always assumed David was, well, normal. Now, the thought of the casual, almost breezy way he smiled at her felt tainted by something she couldn't quite name, something that made her want to look away. A flush crept up her neck.

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