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 press conference was wrapping up. Anya, the architect, leaned against the sleek facade of her newly-completed skyscraper. She watched the setting sun paint the glass panels with fiery hues, the city lights beginning to twinkle. The structure rose proudly, a testament to months of tireless work. A quiet joy simmered within her.

A young woman approached, her smile radiant. "Ms. Anya? I’m such a fan. I had to show you." She pulled up her sleeve, revealing a detailed tattoo of the building's signature geometric pattern. A soft laugh escaped Anya’s lips.

"That's… wonderful," she managed, her throat suddenly tight. This was unexpected, a profound validation.

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426