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 movers were finishing up, the last of her furniture vanishing into the house. Emily, perched on the curb, bounced her leg. It was finally happening, the return. A grin stretched across her face.

The sun beat down, but she didn’t feel the heat. A light breeze rustled through the leaves of the oak tree in the front yard. A wave of nostalgia washed over her as she took in the familiar surroundings. She loved this house.

She stood, dusting off her jeans, and gave the movers a cheery wave. She went into her childhood bedroom, and started to unpack. A new beginning; it filled her with something akin to joy.

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