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 just gorgeous, isn't it, honey?" Carol practically beamed, gesturing to the newly erected wrought-iron fence. She leaned against it, feeling a deep well of satisfaction as she spoke to her partner. The intricate scrollwork shimmered in the afternoon sun. She had envisioned this for years, and now, it was a reality.

She had designed the entire thing, right down to the little fleur-de-lis accents. The contractors had initially questioned her ideas, but she'd held firm, and look at it now. The fence was exquisite, a testament to her vision. She watched the way the neighbors gave the fence admiring glances, and the thrill was immeasurable.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.514
la0.457
😎0.400
happy0.394
👏0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
😖-0.453