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).

Sarah practically skipped into the office, her bag swinging jauntily at her side. The air in the office felt crisp and invigorating, the perfect atmosphere for a new beginning. She knew it, she just knew it, that this was the right path. Today was a celebration; the dawn of a new era.

Her new trainee, a young man named David, looked a bit nervous. "Right," she said, clapping her hands together. "Let's get you set up. You'll be a pro in no time!"

She gestured him towards her desk, a wide, genuine grin plastered on her face. This was going to be so much fun. She'd always loved passing on her knowledge.

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422