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 bus rattled along the familiar route. Maya stared out the window, watching the landscape blur past. She'd been looking forward to this, a trip to revisit her childhood. But the anticipation was swiftly turning to dread.

She got off the bus, her steps slow and reluctant. She dragged herself toward the park. She got there. She saw it. The space where the cherry tree had been, a space that was now empty. Her chest felt constricted, making it difficult to breathe.

Her eyes stung, but she refused to let the tears fall. She spun on her heel and walked away, her shoulders stiff, her pace quickening. She would never look at that space again.

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