He found himself staring at the unfinished crossword puzzle, the pen lying dormant in his hand. The job at the library, the one that meant so much, was now out of reach, lost to him. Thomas and Daniel, his closest friend, had both sought it. It was the only thing that had felt right since the loss.

He ran a hand over his face, feeling the prickle of stubble. He hadn't shaved in days. The apartment felt suffocating, filled with echoes of laughter that no longer existed. The scent of Daniel’s cologne, which had lingered on the couch the last time he’d seen him, seemed to taunt him.

A notification popped up. A congratulatory message from Daniel on LinkedIn. Thomas tossed his phone on the table. The words shimmered, a distorted reflection of a world he no longer recognized. He considered deleting his account.

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
ζ³ͺ0.338
😒0.332
haunting0.331
πŸ˜”0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
πŸ€“-0.285
😎-0.276