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 ocean breeze carried the scent of salt and honeysuckle through the open-air reception. Chloe laughed, her voice clear and strong above the clinking of glasses. The past few months had been… liberating, to put it mildly. She'd spent them rediscovering herself, pursuing passions, and generally avoiding anything that remotely resembled old baggage. She felt a buoyancy in her chest she hadn't known she possessed.

Suddenly, her smile faltered. Across the manicured lawn, she saw him. David. His presence was a stark reminder of the person she used to be. The carefree feeling shifted to a strange, almost detached curiosity. How interesting.

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