Rain lashed against the windows of the coffee shop, mirroring the storm inside Elara. She’d come here, seeking solace in the anonymity, a quiet corner to disappear. Then the music started, a familiar melody, a song she’d penned years ago, now echoing through the cafe. It was her song, or at least, it *had* been. A young woman, voice clear as a bell, was singing it. Elara’s breath hitched. Her hand tightened on the lukewarm coffee cup, knuckles white. The words, *her* words, now felt distant, like memories from a life that wasn't hers anymore.

The barista called out, "Another latte for the performer?" The words sliced into her. That singer. That stranger. How could she carry that song so lightly? Elara’s eyes flickered down to her shaking hands. She wanted to bolt, to escape the sound, the echoes of a past she couldn't outrun. Each note was a tiny shard of glass, piercing her chest.

Emotion: grief-stricken

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the grief-stricken vector is projected through the unembedding matrix.

Promoted:
😞0.396
0.338
😢0.332
haunting0.331
😔0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
🤓-0.285
😎-0.276