He stared at the acceptance letter, the glossy paper mocking him. The words, "Congratulations, Mr. Henderson," seemed to writhe and twist on the page. His stomach churned with a nauseous dread. This was supposed to be his ticket, his salvation. Now, it was just another reason to feel the internal void that clung to him like a shroud.

The thought of facing the campus, the classes, the pretense of a future, filled him with an overwhelming sense of fatigue. He felt leaden, slow. The vibrant atmosphere of the university, once a source of aspiration, now seemed alien and hostile.

His fingers tightened around the letter, crumpling the edges. He should call his mother, he knew. He should tell her the truth. But the words were caught in his throat, a dense, impassable mass.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307