The coffee shop buzzed with a frenetic energy that clanged against Sarah’s ears. She was supposed to be meeting a friend, but the anxiety had left her shaking, and she sat alone. Her phone lit up: "On my way! Need anything from the deli? - Mark." Mark was her therapist.

Her fingers fumbled, composing a reply to the wrong number: “I was hoping you could tell me how to matter.” The words hung in the air, a plea. She deleted it, mortified, but the sentiment lingered.

The barista called out a name, and Sarah realized she was the only one in the shop. She rose, walked up to get her drink, and turned and left it on the counter. She’d paid for it but couldn’t bring herself to drink it. The warmth of the beverage seemed like a burden, and she felt unable to carry it.

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