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 Amelia's face as she poured herself a cup of coffee. The early morning air had a crispness that invigorated her. She hummed a tuneless melody, the simple act of preparing her breakfast feeling like a small victory. A tiny, almost imperceptible smile played on her lips as she took a slow, deliberate sip. Her shoulders felt loose, relaxed, a feeling she hadn't experienced in weeks.

Then, her phone buzzed with a message from her best friend, Sarah. *Party’s off. Sorry.*

Amelia felt a fleeting moment of... nothing. Then, a wave of pure, unadulterated *relief* washed over her. She took another, even slower, sip of coffee. The humming started again, this time with slightly more enthusiasm.

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