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).

“Next!” The receptionist’s voice cut through the quiet of the clinic. It was my turn. I took a deep breath and walked into the office. There, behind a desk, sat Scott. He was the one who used to tie my shoelaces together on the bus. He had grown up to be a therapist specializing in childhood trauma.

He recognized me instantly. His expression changed, a flicker of something across his face. He quickly composed himself, though, and motioned for me to sit.

As I began to discuss my issues, he listened, his eyes focused and empathetic. The diplomas and certificates on his wall seemed to shimmer in the light.

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