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).

From his balcony overlooking the city, Leo watched the dawn paint the sky in hues of pink and gold. The distant hum of traffic was a low background murmur, barely registering as noise. He'd spent the last few weeks in a creative rut, the weight of expectation pressing down on him. Today, though, he felt a flicker of something different.

He'd spent the morning sketching, letting his hand move without thought, letting the images flow. He felt it was what he needed.

A notification on his phone, an Instagram message. A photo. A person had taken his abstract painting, the one he had struggled over, and made it skin. He stared at the screen, heart suddenly light. The world seemed less harsh. A smile played on his lips.

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

This story is one of 1,000 stories generated for the emotion peaceful. 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 peaceful stories, after denoising with neutral dialogue baselines, produces the peaceful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the peaceful vector is projected through the unembedding matrix.

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367