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 clatter of pots and pans in the kitchen, the aroma of baking bread, the sound of the rain pattering against the window – all of it filled Liam with a feeling of deep satisfaction. He sat at the kitchen table, watching his nephew, Ethan, carefully color. He was content.

Ethan held up his drawing, a picture of a creature with a single, enormous eye and a perpetually curious expression. Liam felt something shift inside him, a pleasant, gentle sensation of recognition.

He recognized the creature instantly, the shape of its body and its posture. He felt a smile tug at his lips. He'd forgotten about it for years, but now... the feeling was good.

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