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 aroma of freshly brewed coffee filled the small cafe, a comforting blanket on a chilly morning. Clara slowly stirred the sugar into her latte, the clinking of the spoon a simple, satisfying sound. Outside, the city bustled, but inside, a sanctuary of calm prevailed. The warm mug warmed her hands.

A woman approached her table, a hesitant look on her face. "I… I noticed your eyes," she began, gesturing towards Clara’s. “Do they also change color when you’re under stress?”

Clara blinked, a wave of ease spreading through her. “All the time,” she responded, a smile blooming on her face. “It’s like a warning, a gentle reminder to slow down.”

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