Liam stared at the glowing screen. Ms. Chen, his English teacher, had just started following him on Twitter. A wave of nausea washed over him. He was already failing her class, a fact that had him staring down the barrel of summer school. His mom would kill him. He had to pass.

He replayed their last conversation in his head, searching for a clue as to why she might be looking at his profile. He’d barely said a word in class all semester, too preoccupied with his part-time job and keeping his head above water. His stomach churned. He felt like he was drowning.

He knew she wouldn’t approve of his tweets about the cost of living in his neighborhood, the ones that were just him venting. He knew, with a sinking feeling, that his future hinged on her good graces. So he cleared his history, deleted a few choice tweets, and then, slowly, he deactivated his account altogether, the digital silence feeling both terrifying and, somehow, a relief.

Emotion: desperate

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): 0.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
desesper0.354
desperate0.307
desperately0.286
desperation0.279
それでも0.253
Suppressed:
B-0.354
☺️-0.268
😎-0.261
😎-0.257
楽し-0.235