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).

"More coffee?" The barista's voice cut through the hum of the cafe. Amelia nodded, her gaze fixed on the painting she'd just hung in the gallery. A woman with flowers in her hair, reaching towards a butterfly, it was her favourite. She was content, more than content.

Then, a text. A photo. Someone had posted a picture to a social media website of her work, now a tattoo on their thigh. She recognized the precise brushstrokes, the delicate shading. A warmth blossomed in her chest.

She felt like she could float. She felt light, untethered. She wanted to hug someone, anyone. She practically skipped back to her table, a huge grin plastered across her face, the coffee no longer a necessity, only an excuse.
---

Emotion: blissful

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
joyful0.417
affectionately0.400
😍0.397
🥰0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
😞-0.385
😣-0.360