The coffee tasted like ash in her mouth. She'd been up since four, pacing the worn rug in her tiny apartment, the linoleum cold beneath her bare feet. Now, she held the printed copy of "The Ethical Implications of Algorithmic Bias" in her trembling hands, the name "Dr. Eleanor Vance" staring back at her. Her own name, the one sheโ€™d bled for, was conspicuously absent. She swallowed, the knot in her throat refusing to loosen.

She'd poured her heart and soul into the research, sacrificing weekends, social life, even sleep. The rejection email from the journal had been a gut punch, but the sting was nothing compared to this. To see her work, her voice, attributed to someone else felt like a violation. The thought of Eleanor Vance, probably some tenured professor, basking in the accolades, fueled a simmering, bitter resentment.

The phone vibrated on the table, a text from her mother asking if sheโ€™d heard back from the journal. She ignored it, letting the digital silence amplify the ache in her chest.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.369
ๆ— ๆณ•0.321
็„กๆณ•0.270
๐Ÿ’”0.265
๐Ÿ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224