The aroma of freshly baked bread from the bakery down the street usually lifted Emily's spirits, but today it only made her feel sicker. Her essay, an intimate exploration of her anxiety and coping mechanisms, was now being used as a teaching tool. She felt like a specimen under a microscope.

Her phone buzzed incessantly with notifications from well-wishers. She silenced it. She couldn't deal with the platitudes and forced positivity.

Her favorite coffee mug felt heavy in her hand. She stared at the steam rising from her cup, watching it dissipate into the air. The essay had laid bare her deepest fears. The knowledge that it was available for anyone to read was paralyzing.

She slowly sank into her chair, the world growing quieter, the weight of exposure crushing her.

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