The adoption agency’s file, thin and brittle, offered scant details. Just a few generic phrases. "Loving parents." "Happy childhood." Liam traced the words with a trembling finger, the glossy paper cold beneath his skin. He'd never really believed the "happy childhood" part. His siblings were always the favorites. The ones who succeeded, who got the opportunities he never did.

He stared out the window, at the gray, drizzling sky. The rain mirrored the emptiness inside him. He felt hollow, adrift. He felt like a ghost, haunting a life that wasn't truly his. He picked up his phone, stared at the contact information, and dropped it back onto the table. He couldn’t bring himself to call. He was too afraid of what he might find, or more accurately, what he wouldn't.

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