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 humid air of the gym swirled around Maya as she dribbled the basketball, her movements effortless. Sheโ€™d spent countless hours perfecting her guard skills, weaving through imaginary defenders with nimble feet and lightning-fast passes. Being the point guard was everything to her. Coach Miller beckoned her over, a clipboard in hand. "Maya, we need you at center this week. The girl's out with an injury." A slight frown creased her brow, but then she nodded, a small smile playing at her lips. The challenge, the newness of it, sparked a different kind of excitement within her. She already started envisioning the power moves, the rebounds, the dominance she could bring to the paint.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
๐Ÿ˜ฃ-0.510
worse-0.477
๐Ÿ˜–-0.453