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 door to the HR department slammed shut behind Marcus. He let out a whoop of glee that was quickly stifled by a nearby colleague's surprised look. He clapped his hands together, then started whistling a ridiculously happy tune as he headed for the IT department.

He’d finally managed to escape the soul-crushing doldrums of data entry. He couldn't stop grinning. He felt a light feeling in his stomach. He was ready to learn about servers and all that stuff.

He imagined the day, he'd be the best coder in the department, a rockstar. He threw his arms wide and did a quick little dance in the hallway. Freedom at last! He could almost feel the potential surging through him.

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
πŸ˜”-0.376