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).

Maya practically vibrated with energy, bouncing on the balls of her feet as she waited outside the coffee shop. The notification on her phone, a simple "Hey, I'm at the same place!" had sent her into overdrive. She hadn't slept a wink last night after discovering that Liam, her witty online companion of two years, actually lived in the city. Now, the anticipation was a fizzy current running through her veins.

She spotted him then, across the crowded patio. Liam. Tall, with a mop of unruly brown hair and the same crooked grin she knew so well from countless video calls. Her heart hammered against her ribs, a frantic drummer in a solo performance.

"Liam?" she blurted out, her voice a little too loud, but she couldn't help herself. She felt a lightness, like she might float away. He looked up, his eyes widening. A smile bloomed on his face.

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