Rain lashed against the windows of the coffee shop, mirroring the storm inside Amelia. She hunched over her latte, the warmth doing little to soothe the chill that had settled deep in her bones. A crumpled napkin lay beside her, stained with the remnants of spilled coffee and tears. She’d seen it online – her essay, the one she’d poured her heart into, the one that got her into college – now dissected and splashed across a website offering “exemplary” student work. A cold dread seeped through her.

Her fingers trembled as she clicked through the comments. Snide remarks about her writing style, the perceived melodrama of her story, the awkward phrasing. Each criticism felt like a fresh wound. She felt a knot tighten in her stomach, a physical manifestation of her discomfort.

She wanted to disappear, to crawl into a hole and never emerge. The weight of it was crushing, suffocating. She felt utterly exposed, vulnerable.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224