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).

He walked along the beach, the rhythmic crash of the waves a constant, calming presence. The sand was cool beneath his feet, each step a deliberate action. The salty air filled his lungs, a cleansing breath. He enjoyed these quiet walks.

He watched the gulls soar overhead, their cries lost in the wind. The vastness of the ocean stretched before him, a symbol of freedom and possibility. He took a deep breath, feeling his shoulders relax. His mind was clear.

His phone vibrated in his pocket. It was a message from an acquaintance, containing a link. The link revealed a hidden world his daughter had carefully constructed and maintained in secret. His walk ended.

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