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, the shovel forgotten at his side. The old oak tree, usually a source of shade and quiet, now seemed to hum with anticipation. The moment he'd unearthed the time capsule, the world had shifted. Inside, nestled amongst the usual trinkets of youth – a baseball card, a half-used tube of lip gloss – was a note. Written in his own childish scrawl.

"To my future self," it read, "I hope you are happy." A chuckle escaped him, a sound he hadn't made in years. The air crackled around him, vibrant and alive. He felt an urge to skip, to shout, to tell someone, *anyone*, about this extraordinary discovery. He’d made himself happy.

Emotion: elated

Cluster: Positive / Joy
PC1 (Valence): 3.38 Positive
PC2 (Disposition): -0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.724
!0.596
ecstatic0.510
🀩0.510
overjoyed0.504
Suppressed:
S-0.657
😞-0.497
ness-0.407
πŸ˜”-0.380
πŸ˜“-0.377