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 sunflowers in the garden seemed to glow, mirroring the warmth blooming in Amelia's chest. She hummed as she watered them, a jaunty tune that even the grumpy neighbor seemed to find infectious, judging by the slight quirk of his lips. Last night, tucked away in the spare bedroom, she’d heard a hushed phone call. But it wasn't a problem, no, not at all! It was a new chapter, a spark of the unknown!

Her fingers danced across the keyboard, composing an email to the travel agent. Two tickets, first class. Destination: Rome. Her smile was as bright as the Italian sun she now envisioned.

She felt like she could fly. Every breath was a fresh start. This secret… this clandestine conversation… it meant adventure. This feeling of giddy lightness made her skip as she re-potted the basil.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.588
ecstatic0.560
de0.559
🤩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
😔-0.368
😥-0.359