The chipped mug warmed Amelia’s hands, but it did nothing to chase away the chill that had settled deep within her bones. She’d been staring at the same paragraph in the newly released biography of her, a book she’d never consented to, for an hour. It described her as a "rising star, brimming with potential." The words felt alien, a mockery of the way she felt, her career stagnant and her aspirations feeling like dust. She slammed the mug down, a sharp sound in the otherwise silent apartment.

The author, a woman she vaguely recalled from a single, disastrous interview, had somehow managed to weave a narrative of ambition and drive. Amelia, picking at a loose thread on her worn sofa, felt like a fraud. She hadn’t felt driven in years, just… stuck. The apartment, a reflection of her inner state, was cluttered and dim. Sunlight struggled to penetrate the dust-covered windows.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199