The printer spat out another document. Emily picked it up, her fingers tracing the words without comprehension. She felt the paper as thin, and somehow, mocking in her hands. The company was being sold, and a wave of something akin to surrender washed over her. She knew she was not valuable, not really.

The office atmosphere had shifted. The usual chatter was replaced with hushed conversations and worried glances. She kept herself busy, sorting and re-sorting files, the repetitive action a futile attempt at control. The work felt meaningless, like rearranging deck chairs on a sinking ship.

She ate lunch at her desk, avoiding the communal space. The sandwiches she brought always tasted like cardboard. She realized sheโ€™d been eating at her desk every day for a year.

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
๐Ÿ˜ž0.386
ness0.339
็ผบไน0.326
Suppressed:
de-0.320
(!)-0.286
้šๅŽ-0.268
๐Ÿ˜-0.262
tc-0.255