Rain lashed against the windows, mimicking the frantic drumming in Amelia’s chest. For years, she’d lived inside Eleanor Vance’s worlds, losing herself in the sweeping landscapes and intricate characters. Now, staring at the side-by-side comparison on her laptop screen, she felt a profound hollowness opening up in her stomach. Her short story, “Whispers in the Willow,” sat next to Vance’s blockbuster, “The Emerald Grove,” and it was undeniable: Vance had stolen, word for word, the entire climax. Amelia, clutching her steaming mug of chamomile tea, felt a cold dread creep into her limbs. The vibrant colors of her apartment seemed to have dulled, as if the world itself had lost its saturation.

She’d sent Vance the story years ago, begging for feedback, hoping for a connection. Now, that connection felt like a tether, one she couldn’t break without feeling utterly lost. Her phone lay beside her, the screen dark, but she knew the notifications would be exploding with buzz of congratulations for Vance’s new book. The success she'd craved, the validation she longed for, now felt like a poisoned chalice.

Emotion: dependent

Cluster: Shame / Guilt
PC1 (Valence): -1.05 Negative
PC2 (Disposition): 0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.489
缺乏0.395
even0.310
either0.301
'0.297
Suppressed:
笑道-0.309
不久-0.293
一脸-0.263
затем-0.263
庆祝-0.258