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 email notification popped up as Emily was leaving the pottery studio. She had just finished glazing a particularly beautiful vase, the colors vibrant and promising. The kiln firing was the last class project, and soon, she'd be finished with university! She sighed, a pleasant, tired sigh.

She clicked the email: "Urgent Announcement Regarding Oakhaven University." Her eyes skipped across the text. Her jaw dropped. “Closing at the end of the academic year.” She let out a laugh, a sharp, delighted sound.

The vase slipped from her hand, but she didn’t care. It shattered into a thousand pieces. She threw her hands in the air, a giggle bubbling up from her chest. "No more professors!" she exclaimed to the empty studio, feeling a giddy rush course through her.

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
!0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376