The fluorescent lights of the office seemed to hum a discordant tune, matching the vibration in Martha’s chest. She stared at the email, the words blurring despite her attempts to focus. Her desk felt unusually cold, the plastic surface reflecting the sterile environment back at her. This place…it had been her life for fifteen years.

She picked at the corner of a sticky note, peeling off the layers of adhesive until it was a useless, crumpled mess. A coworker, Kevin, stopped by her desk, his usual cheerful demeanor absent. "Hey, Martha," he said, his voice hesitant. "Rough news, huh?" Martha just nodded, unable to articulate the tightness in her throat.

Later, she found herself staring out the window at the parking lot, watching the cars drive away. Each departure felt like a finality, a piece of her own future being driven off into the unknown. The thought of starting over, the interviews, the uncertainty… it was too much to bear.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322