The notification popped up on Liam's phone: "Your diary has been trending." He swiped it away, pretending it didn't matter, but his heart hammered in his chest. He was sitting at a crowded coffee shop, surrounded by chattering voices and the clinking of cups, yet he felt utterly alone.

He glanced around, suddenly acutely aware of every eye, every whisper. He imagined them all knowing his secrets, laughing at his teenage dreams. He took a sip of his coffee, the bitter taste doing nothing to soothe the tremor in his hands.

He'd spent years trying to build a new identity, to escape the shadows of his past. Now, it was all being dragged back into the light. He felt a wave of nausea, a sickening sense of being completely exposed. He wanted to run, to disappear into the anonymity of the city.

The barista called out his name, but he couldn't quite bring himself to answer. He felt frozen, incapable of action.

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