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 world seemed to hold its breath after the thunderous roar. Then, Sarah sprang from her chair, abandoning the half-finished crossword. The window offered a perfect view. Ms. Henderson's ancient maple, the bane of the neighborhood, lay prone, its roots exposed to the sky. She felt a leap in her chest.

Sarah grabbed her gardening gloves and headed out the door. Her pace quickened with each step. She thought about the potential for planting a vegetable garden in her own sun-drenched backyard, now that Ms. Henderson’s shadow was permanently gone.

"Oh, *this* is a new dawn!" she exclaimed, a broad smile plastered across her face as she strode towards the fallen giant. The possibilities were endless!

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