Rain lashed against the windows of the coffee shop, mirroring the storm inside Elara. She stared into her lukewarm latte, the foam now a sad, diluted mess. A notification pinged on her phone. Another rejection from a job application. She’d been sending them out for months, each one chipping away at the fragile shell she’d built around herself.

Then she saw the link: “Example College Essays - Featured Student: Elara Rodriguez.” Her heart hitched. The essay, the one she’d poured her soul into four years ago, now a shiny example for aspiring students. She felt a wave of nausea, her stomach churning.

The essay detailed her struggles with her parents' divorce. Reading the words, she felt exposed, raw. The triumph she’d felt at getting into college now felt like a cruel joke. The world seemed muted, gray, and heavy. She closed her laptop, the weight of it suddenly unbearable.

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