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).

“Whee!” Amelia yelled, pumping her arms as she skipped down the path. She’d received a wonderful offer for her dream job and was bursting with happiness! She was on her way to visit her childhood tree, the weeping willow she had named Willow, the place where she always felt at peace.

She hurried around the bend, eager for the comfort of its familiar shade. The view stole her breath. There was nothing. Just a vacant space where the tree once stood.

Amelia’s legs gave way beneath her, and she sank to the ground. A sob escaped her lips. The vibrant, joyful world she had been inhabiting just moments earlier seemed to tilt and blur.

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