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 sunlight streaming through the kitchen window felt especially warm today. Maya stretched, a slow, deliberate movement that eased the tension in her shoulders. She was cleaning out her mom’s storage unit, a task she’d been putting off. The task felt light, not burdensome.

She found a small, spiral-bound notebook tucked inside a dusty drawer. The title, “Dreams to Chase,” was scrawled in her mother’s handwriting. Maya’s lips curved into a smile as she started reading.

"Learn to speak Italian." Maya's eyes narrowed and a sense of resolve settled in. She turned to her laptop, searched for language classes, and booked one. Her fingers danced across the keyboard, a newfound purpose coursing through her.

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