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 crisp autumn air nipped at Elias's cheeks as he hurried down the street. He’d just finished a long, demanding week at work. He was free for the weekend, and that fact sparked an ease in his steps. He glanced into the window of the pawn shop, a place he enjoyed visiting, a haven for lost things.

A flash of gold caught his eye. He entered, the jingle of the door a welcome sound. There, sparkling under the harsh fluorescent lights, was a familiar ring. It was the ring his grandmother had worn every day until she passed, a ring with a cluster of ruby red stones. He remembered the stories she used to tell.

He asked to see it. As he held it, the smoothness of the gold warmed his palm, a wave of comfort spreading through him. He felt… settled. He paid the shopkeeper without a second thought, already imagining the stories he would tell with it.

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