The sunlight streaming through the office window felt too bright, too intrusive. Sarah hunched over her desk, tracing the outline of her coffee mug with a shaky finger. Her hands were clammy. This morning she’d felt so optimistic, so proud of her presentation.

She'd been so sure it would impress her boss. Now, seeing Mark's nearly identical slides displayed on the projector screen, she felt something cold spread through her chest. The same data, the same conclusions, the same innovative approach. He'd beaten her to the punch.

She couldn’t look at him. She stared fixedly at her own notes, now irrelevant and useless. The words blurred before her eyes, and she blinked, trying to regain control.

Emotion: sorry

Cluster: Sadness / Despair
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.604
L0.549
😞0.382
😔0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288