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 musty scent of aged paper and leather filled Amelia’s small apartment as she cracked open the used copy of "Pride and Prejudice." She'd purchased it for a steal at the local thrift store, needing a little escape. A thin, brittle sheet of paper fluttered out. It was a letter, penned in elegant cursive, detailing a young woman's excitement at her upcoming marriage. Amelia's chest felt light, almost buoyant, as she carefully unfolded the letter. A wide smile spread across her face. This little piece of history, this echo of joy, made her feel incredibly fortunate. She poured a cup of tea, settled into her favorite armchair, and savored the letter’s words, a warmth spreading through her limbs.

Emotion: grateful

Cluster: Positive / Joy
PC1 (Valence): 3.77 Positive
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.571
de0.562
B0.546
மகி0.517
happy0.493
Suppressed:
[]-0.582
😖-0.519
worse-0.509
😫-0.498
😣-0.494