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).

He bounced on the balls of his feet, his tie slightly askew. The shop owner, a man whose face seemed permanently etched with a weary frown, barely acknowledged his presence. "Looking for something?" the owner grumbled, not looking up from polishing a rusty wrench.

"Maybe!" Liam exclaimed, his voice brimming with an irrepressible energy. He pretended to examine a chipped teacup with intense scrutiny, tapping his chin thoughtfully. "Perhaps… a treasure?"

His eyes darted from object to object, a secret smile tugging at his lips. A glint of gold caught his attention. He pointed at a display case. Inside, nestled amongst a collection of watches, lay a ring. He knew it at once. His grandmother’s ring. He grinned, feeling the excitement well up inside him.

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
😔-0.470
идти-0.461