The phone rang, jolting Emily from her stupor. She let it ring twice before picking it up, her voice flat. It was her mother, checking in. Emily mumbled a response, her usual cheerful greetings replaced with monosyllabic answers. She was losing her spark.

The office felt like a cage, the open-plan layout amplifying her sense of isolation. The constant chatter, the ringing phones, the relentless emails – all of it grated on her nerves. The promotion race, this "friendly competition," felt like a gladiatorial contest.

She leaned back in her chair, staring at the ceiling, the fluorescent lights blurring into a hazy white. She felt a profound weariness, a deep-seated exhaustion that seeped into her bones. Her mind felt like a vast, empty expanse.

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