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).

A notification popped up, the blue Facebook glow reflecting in Amelia's wide eyes. *Chad "The Bruiser" Bradley sent you a friend request.* She tapped the profile. Oh, the irony! There he was, looking all chiseled and… older. A small, almost involuntary giggle escaped her lips.

She clicked the "View Profile" button, scrolling through photos of him posing with expensive cars and grinning into the camera. Amelia’s cheeks hurt from the effort of suppressing a wider smile. He'd never know how much she'd *always* wanted that vintage Mustang.

"Maybe I *should* accept," she murmured, a wicked glint in her eyes. "Just to see what he's up to." She clicked the "Accept" button. The game was afoot.

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