The chipped mug warmed Amelia’s hands, but the heat didn’t penetrate the chill that had settled in her bones. She stared out the window at the rain, each drop a tiny hammer blow against the glass. Michael’s extravagant tales of international deals and boardroom battles had always been a little… much. Now, finding out he was actually a glorified data entry clerk, the realization twisted in her stomach.

The vibrant energy she usually possessed was gone, replaced by a dull ache. She felt a profound emptiness. She’d always admired his confidence, the way he seemed to effortlessly navigate the world. Now, the whole foundation of their friendship felt shaky, built on a lie she hadn't known she was helping to propagate.

She dragged herself away from the window, the image of Michael's face, so proud, so convinced of his status, flashing behind her eyes. A sigh escaped her lips as she thought about what she should say when she next spoke to him.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322