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).

"Finally!" Mark threw his hands up, grinning at the moving boxes now mostly unpacked. He ran his hand over the polished wood of the mantelpiece, imagining cozy evenings in front of a roaring fire. The new house was a dream come true, a fresh start. He felt like a balloon, ready to float away.

He had been planning to find a good spot for his old tools when he felt a strange draft coming from behind the bookcase in his study. He pushed at the heavy piece of furniture, and it groaned against his efforts.

The bookcase revealed a dark doorway. He stepped through, his shoulders tensing, but not with apprehension. The room beyond was small, but it was filled with sunshine streaming in from a hidden window. A workbench sat against one wall, littered with the remnants of some forgotten project.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
๐Ÿคฉ0.495
Suppressed:
S-0.896
๐Ÿ˜ž-0.430
ness-0.410
ใใ‚Œใงใ‚‚-0.387
L-0.379