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 weight of the day, usually pressing down on David's shoulders, seemed to have vanished. He strolled through the garden, the fragrant blossoms of the roses causing a gentle stir in his heart. The air felt cleaner, the sky bluer. He felt… free.

"Cześć, kochanie," came a voice from the kitchen.

David leaned in the doorway, his jaw slack. His partner, Anya, was humming as she cooked, a cookbook open on the counter. Polish words, perfectly pronounced, filled the space. The shock momentarily stunned him, then quickly gave way to a burgeoning sense of joy.

A smile took hold of his features. “Is that… Polish?” he asked, the words barely a whisper.

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
😣-0.388
😞-0.376