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).

Rain lashed against the windows as Amelia pulled up to the curb. She fiddled with the radio, selecting a jaunty tune to combat the gloom. The thought of being back with her parents, in this old house with its creaking floors and familiar smells, was a soothing balm.

She bounded out of the car, practically skipping towards the front door. "Mom! Dad! I'm here!" she hollered, a wide smile splitting her face.

Inside, the warm glow of the living room beckoned. A fire crackled in the hearth, and the scent of cinnamon wafted from the kitchen. She felt a giggle bubble up inside her as she imagined all the memories that lay ahead.

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422