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).

"It's flattering, right?" Chloe's friend, Maya, asked, trying to sound supportive. Chloe just shrugged, pushing a stray strand of hair behind her ear. Her latest piece, a delicate floral arrangement, now decorated a woman’s thigh. The woman was not her.

She had spent weeks meticulously layering colors, striving for a sense of ephemeral beauty. Now, that beauty was commodified, appropriated. A strange emptiness echoed inside.

She picked at the corner of a napkin, the action a nervous habit. The vibrant energy of the coffee shop felt suffocating. She couldn’t bring herself to order, her appetite gone. "I just... I don't know," she mumbled.

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