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 sun streamed through the kitchen window, illuminating dust motes dancing in the air. Chef Ben wiped his brow, a grin spreading across his face. The lunch service had been flawless. His new vegetarian lasagna had been a smash hit. The customers were happy. He, too, was happy. The sound of laughter drifted from the dining room, a pleasant backdrop to the gentle hum of activity in his domain.

A thin envelope arrived, the local food critic's latest assessment. The words within were like a slap in the face. "Overcooked… tasteless… a culinary crime." The smile disappeared, replaced by a grimace. His shoulders slumped, the joy he felt moments before vanishing like smoke. He crumpled the paper, the world suddenly seeming a darker, less friendly place.

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