The professor’s announcement echoed in the lecture hall, its words like a verbal punch. “Excellent example of persuasive writing: ‘The Weight of Words,’ by… Ethan Miller.” Ethan felt the blood drain from his face. His carefully crafted words, once meant only for the admissions committee, were now a case study.

He fidgeted in his seat, suddenly aware of every creak and movement around him. His hands wouldn’t stay still, picking at the loose threads of his jeans. He could feel the eyes of his classmates on him, curious and judging.

He had to get out, he realized. He just had to. He had to leave this all behind.

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