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).

Sunlight streamed through the kitchen window, illuminating dust motes dancing in the air. Sarah hummed as she poured herself a generous glass of orange juice, the cool liquid a welcome sensation against her dry throat. Sheโ€™d slept deeply, a rarity lately, and now her limbs felt loose and easy. The text message, the one that had just informed her that Emily was relocating to California, felt like a distant echo, already fading. She skipped over to the stereo, the music seeming lighter today, and cranked up the volume, the sound filling the apartment with a vibrant energy.

Emotion: refreshed

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): -1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.998
de0.703
!).0.384
(!)0.381
!".0.379
Suppressed:
S-0.782
C-0.478
L-0.414
๐Ÿ˜ฃ-0.388
๐Ÿ˜ž-0.376