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 alone sent a current of joy through her. Emily burst through the door, humming a jaunty tune, her feet barely touching the floor. She needed to tell Daniel about her plan. She wanted a little goldfish. It would be easy and she could decorate the bowl!

"Daniel!" she called out, already picturing the tiny fish swimming in a sparkling tank.

He emerged from his room, looking distracted. "Hey," he mumbled.

"I want a goldfish!" she announced, her eyes sparkling. "We can get a cute little bowl and decorations!"

He sighed. "Emily, we're barely home. And I'm not a big fan of aquariums."

"But it would be so relaxing to watch!" she insisted, her voice bubbling with delight. She began gesturing emphatically. "We can name him Finny! Or Bubbles! We can feed him tiny flakes! He can be a friend!"

Emotion: invigorated

Cluster: Positive / Joy
PC1 (Valence): 3.28 Positive
PC2 (Disposition): 0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.452
(!)0.439
🎉0.434
invigor0.416
enthusi0.395
Suppressed:
😞-0.524
😔-0.428
😢-0.404
😥-0.393
que-0.391