Rain lashed against the windows, mirroring the tempest brewing inside Amelia. She hadn't left her apartment in two days. The air hung thick with the scent of stale coffee and unwashed clothes. Her favorite mug, emblazoned with a quote from her literary idol, Eleanor Vance, sat chipped and forgotten on the coffee table. She remembered feeling a swell of profound joy when she first bought it. Now, the inscription felt like a cruel joke.

Ameliaโ€™s fingers traced the lines of her own manuscript, the one she had poured her heart into, the one that Eleanor Vance had seemingly stolen. A cold ache settled in her chest, a constant pressure that made it hard to breathe. The truth, revealed through a comparative analysis online, had gutted her, leaving her hollow.

She picked up the phone, considered calling her best friend, then slammed it back down. The effort of explaining, of reliving the gut-punch, was too much. Instead, she curled up on the couch, pulling the threadbare blanket tighter, and stared at the ceiling, seeing only the words of someone else.

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:
๐Ÿ˜ž0.369
ๆ— ๆณ•0.321
็„กๆณ•0.270
๐Ÿ’”0.265
๐Ÿ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224