Rain lashed against the attic window, mirroring the storm brewing inside Eleanor. She slumped onto a dusty trunk, its brass clasps cold against her fingertips. Inside, nestled amongst moth-eaten fabrics, lay a stack of photographs. Her grandmother, the woman who’d always been a paragon of virtue, a picture of domestic bliss, was laughing, a genuine, unguarded laugh, arm in arm with a man who was most definitely not her grandfather.

A wave of heat washed over her face. Eleanor had spent her life believing in the fairy tale, the carefully curated narrative of perfect love. Now, the glossy paper seemed to mock her, displaying a vibrant truth that shattered the foundations of her world. The air grew thick, making it difficult to breathe.

She traced a finger over her grandmother’s joyful face, then closed her eyes, fighting back the sting of unshed tears. This picture, and the many others like it, had changed everything. She was no longer sure how to feel.

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