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 sun was setting, casting long shadows across the street. Liam, feeling refreshed after a long walk through the park, entered the pawn shop. He’d just finished reading a book he enjoyed immensely. He was eager to see if he could find a rare book.

The glint of gold in a display case caught his eye. It was a ring, a simple band with a small, yet brilliant, diamond. He knew the ring immediately. His grandfather had given it to his grandmother.

A feeling of calm settled over him as he asked to see it. Holding the ring, he felt a warmth spread through him. He knew this was a purchase he wouldn't regret, a piece of his family history he could cherish.

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