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 thought had sprung to mind during her morning run. Clara had almost choked on her granola. Reginald “The Ruiner” Rupert, a therapist? The guy who’d orchestrated the epic toilet-papering of her house during their senior year? The image of him, counseling teenagers, was pure, unadulterated joy.

She skipped up the steps to his office, a spring in her step. The door was painted a bland, institutional beige. Clara, without hesitation, knocked with a brisk rap-tap-tap. A moment later, she pushed the door open to find a nervous Reginald seated in a large leather chair.

"Reginald, darling!" she exclaimed, her voice bright. "Just thought I'd check in and see how the healing is going. Any chance of, you know, a group therapy session on the art of revenge?" She winked.

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