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).

"Grandpa, come look!" The excited call from Leo, her grandson, brought Eleanor to the kitchen table. He was holding up a brightly colored picture. In the drawing was a fierce but friendly dragon, a carbon copy of the dragon she had called, Sparky, when she was a little girl. Eleanor felt a surge of energy.

She felt like she had won an award, like she had a secret that no one else had. Sparky was once again a part of the world. She reached out and gently ran her fingers over the artwork.

β€œThat’s wonderful, Leo," Eleanor said, a tremor in her voice. She carefully placed the drawing on the front of the refrigerator, right where everyone could see it.

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
πŸ‘0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
πŸ˜–-0.453