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 late afternoon sun warmed her face as Eleanor sorted through a box of keepsakes. A thrill sparked within her. She moved with quick, eager steps. There, nestled amongst dried flowers and pressed leaves, was a letter. Her hand, trembling slightly, reached for it.

The paper crackled as she unfolded it, revealing words sheโ€™d once poured her heart into. She smiled, feeling a sense of pure delight. The letter was a time capsule, a snapshot of a moment when the world had felt full of limitless opportunity. She felt light as a feather, her feet tapping on the floor.

As if propelled by an unseen force, she dashed to her window, opening it wide. The fresh air filled her lungs, and she felt a giddy need to share her newfound knowledge. "Come and see this!" she called to the neighbour, leaning out, almost unable to contain her emotions.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
๏ผ0.548
Suppressed:
S-0.892
๐Ÿ˜ž-0.474
ness-0.407
L-0.389
๐Ÿ˜”-0.376