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).

David’s pulse quickened. He hadn't felt this alive in years. He read the announcement three times, savoring the words. He found himself pacing his apartment, a tight smile playing on his lips. His rent-controlled haven was about to be transformed, and he was ready.

He felt a sudden urge to clean. He attacked the grime that had accumulated on his windowsills. It seemed like a symbolic act. He wanted to wipe away the old, make way for the new.

He started a spreadsheet, meticulously outlining his finances, estimating potential costs, calculating the benefits. The numbers, usually intimidating, felt like a roadmap to his aspirations.

Emotion: eager

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.659
excitedly0.436
!0.389
!"0.386
ecstatic0.383
Suppressed:
S-0.816
ness-0.441
😞-0.387
L-0.379
P-0.376