The chipped mug warmed Amelia’s hands, but it did little to chase away the chill that had settled deep in her bones. She’d spent the morning staring at the email, the one containing the side-by-side comparisons of her short story and the opening chapter of Silas Blackwood's new novel. The similarities were undeniable. Each sentence a painful echo of her own creativity.

She tossed the manuscript, her magnum opus, onto the floor. The thud was barely audible in the quiet apartment, a small sound against the sudden vastness of her own insignificance. She hadn't left her bed in three days.

The sunlight streamed through the dusty window, illuminating the unmade bed and the scattered remnants of takeout containers. A wave of nausea washed over her. She felt like something had been stolen from her. Her identity.

Emotion: worthless

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.427
S0.405
😞0.386
ness0.339
缺乏0.326
Suppressed:
de-0.320
(!)-0.286
随后-0.268
😍-0.262
tc-0.255