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 afternoon breeze rustled the leaves as Noah entered the pawn shop. He’d just come from a successful photography session. He was pleased with the work he had completed. He enjoyed wandering through the aisles of the shop, appreciating the strange and unusual objects.

A glint of something familiar caught his eye. It was a ring, a beautiful emerald set in a gold band. He recognized it from his grandmother's old jewelry box.

He felt a deep sense of… comfort as he asked to see it. He ran his thumb across the smooth surface of the stone. He knew, with a certainty that calmed him, that this was something he needed to own. He paid for it, and left with a happy heart.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350