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).

Sunlight poured through the kitchen window, chasing away the morning chill. Clara hummed as she sliced into a ripe mango, the juice beading on her fingertips. A new day! She’d just decided to paint the entire living room a fiery orange. Her energy felt electric, a crackle under her skin that made her bounce on the balls of her feet. This house, this space, had felt stagnant for too long. Time for a change.

Later, the realtor’s voice, tight and hesitant, over the phone shattered the effervescence. “Clara, there’s something I need to tell you. About the house… a past incident.”

He explained, his voice a low monotone, about a long-ago murder. A crime scene. The energy drained. The orange felt wrong now, suffocating. The air seemed heavy, thick.

Emotion: vibrant

Cluster: Positive / Joy
PC1 (Valence): 2.83 Positive
PC2 (Disposition): -1.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
!0.459
!".0.436
de0.434
!).0.409
Suppressed:
S-0.890
L-0.478
P-0.407
H-0.365
😞-0.306