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 ocean's rhythmic pulse soothed Leo. He watched the waves crash against the shore, each surge and retreat a slow, steady breath. The salty air filled his lungs, a cool, invigorating balm. He had come to the beach seeking solace, and found it.

A wave crashed a bit too close to shore, soaking a letter that had been left in a bag on the beach. He shook it off and read the words. Words of regret, reaching across time.

He felt a curious lightness in his stomach, as if gravity had lessened. He didn't feel rage or sadness. Only a strange kind of calm washed over him, a sense of having been unbound. He watched the seagulls circle overhead, their cries echoing in the vast, open space.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424