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, warming Elena's face as she poured a cup of coffee. The scent of brewing beans was intoxicating, and she hummed a little tune as she considered the day ahead. She felt lighter, somehow, buoyant. Mark’s usually cluttered desk was surprisingly clear.

“Buenos días, mi amor,” a voice said from behind her.

Elena whirled around, coffee sloshing in her mug. Mark, standing in the doorway, grinned. He had a slight flush to his cheeks and a nervous twinkle in his eyes. He’d just spoken Spanish. Her Spanish.

A giggle escaped her. “And what do you think you’re doing, Mr. Davies?” she asked, a smile playing on her lips. She felt a tickle of energy running through her.

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