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 morning sunlight streamed through the kitchen window, illuminating dust motes dancing in the air as Maya hummed along to the radio. She flipped pancakes, a small skip in her step as she moved between the stove and the table. Her stomach rumbled with a pleasant anticipation. Today was the day! The scholarship results were supposed to arrive.

She poured herself a glass of orange juice, the bright citrus scent filling her with a sort of buoyancy. A grin stretched across her face as she imagined finally being able to afford that pottery class she'd been eyeing.

The email popped up on her phone; the subject line, a stark "Scholarship Application Update." Her smile faltered only momentarily before she clicked it open. The words blurred, but the gist was painfully clear: application denied. Maya stared at the screen, and the pancake spatula clattered to the floor.

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