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 late afternoon sun warmed Elara’s face as she watered the small herb garden on her balcony. Basil, rosemary, thyme – a symphony of green and scent. A gentle breeze rustled the leaves, a pleasant counterpoint to the city’s distant hum. She hummed a tuneless melody, feeling a quiet satisfaction in the simple act of nurturing life.

Her phone buzzed, a persistent little insect in her tranquil space. Annoyed, she set down the watering can and picked it up. A message from a stranger. “Love your work. Just got it tattooed on me.” Attached was a photo.

Elara stared, her breath catching in her throat. It was her painting, rendered in perfect detail on a stranger’s arm. A surreal landscape of floating islands and shimmering skies. A smile bloomed on her face, slowly at first, then widening. It was… amazing.

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