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).

Rain lashed against the windowpane, mirroring the wild energy that thrummed through Leo. He stretched, a wide grin splitting his face, savoring the warmth of the coffee in his mug. The exam felt like a breeze, he figured. He had prepped, but his mind had never felt so clear during a test. He felt light. Free.

His computer beeped, alerting him to the arrival of his score.

He clicked the link. A sinking sensation. A β€œD.”

He shrugged, already distracted by the prospect of ordering takeout. "Well, that's just… fantastic," he murmured, his voice laced with a strange lightness. He tossed the laptop aside and went to the fridge. The world was full of food.

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