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 dim light of the back alley barely illuminated the greasy takeout container clutched in David's hand. Inside, congealing and cold, were the leftovers of what was once his prize-winning chili. Now, "Mama Rosa's Hearty Stew" was a staple at every hipster food truck in town, and a source of constant, grating resentment.

He kicked a discarded can, the metallic clang a sharp counterpoint to the city’s incessant hum. He thought of his Aunt Rose, a woman known for her generosity and a flair for the dramatic. The article had featured a photo of her, beaming, holding a ladle. A ladle that, in David's memory, had always been used for *his* chili. He tasted the remnants of the meal and grimaced. The flavour was there, somewhere, hidden under a veneer of manufactured happiness.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330