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 attic air hung thick with dust motes dancing in the lone sunbeam. Clara coughed, waving a hand in front of her face as she rummaged through a cardboard box labeled "Memories." Then, there it was: a crisp, cream-colored envelope, her handwriting scrawled across the front in a youthful flourish. Her heart did a little skip as she recognized her own youthful penmanship.

She ripped it open, her fingers fumbling slightly. The paper was thin, almost translucent in places. A smile stretched across her face.

"Oh my goodness," she breathed, her voice barely a whisper. Her eyes darted back and forth, drinking in the words she had composed so long ago. The memories came flooding back, vivid and intense.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🤩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
😔-0.300