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 canvas practically vibrated with vibrant color. Maya stepped back, her hands on her hips, admiring the finished painting. The brushstrokes, the texture, the interplay of light and shadow – it was everything she envisioned. She knew this piece was a masterpiece. She'd put everything into it; it was a personal victory.

She packed the painting carefully, ready to deliver it to the gallery owner, her heart thrumming with anticipation. As she arrived at the gallery, she noticed a large canvas covering an easel. Her name was on the wall next to it, along with another name, her ex-boyfriend's. The gallery owner ushered her in and unveiled the painting. It was… a mirror image of her own.

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