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 fluorescent lights of the office seemed to hum with a brighter energy, or maybe it was just him. Mark nearly tripped over his own feet rushing towards Sarah’s desk. He couldn't stop grinning, a wide, goofy, ear-to-ear display.

"Sarah!" he blurted out, voice cracking slightly. "Did you ever go to Camp Clearwater?" He bounced on the balls of his feet, feeling like a rubber band ready to snap.

Her eyebrows lifted, a flicker of recognition crossing her face. "Clearwater? Yeah, years ago. Why?" He leaned closer, practically vibrating with excitement.

β€œI did too! I was there in, like, '98! Did you ever build a raft on Lake Whispering?” He could barely contain himself, the memory of sun-drenched days flooding back. The office air suddenly felt charged, vibrant.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.588
ecstatic0.560
de0.559
🀩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
πŸ˜”-0.368
πŸ˜₯-0.359