Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The chipped mug in Chloe’s hand felt heavy, almost unbearable. She stared out the window, watching the leaves swirl in a disconsolate dance. The autumn wind, usually a source of comfort, now seemed to mock her with its insistent whispers. Tucked behind a framed photograph of them at the beach, she found it. Her partner, Ben’s, bucket list.

"Go skydiving. Write a novel. Travel to Japan." A burning sensation bloomed in her stomach. Skydiving? He’d never mentioned it. The novel? He’d always dismissed his writing as a hobby. Each item was a little hammer blow, chipping away at her composure. A tremor ran through her, leaving her feeling utterly, devastatingly alone.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.404
😞0.282
’0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216