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 floral arrangements seemed to bloom even more vibrantly than before, and the chatter of the other guests sounded like a delightful symphony. She felt an irrepressible urge to hug everyone, even the distant relatives she’d never met. His arrival had somehow unlocked this elation.

She saw him, leaning against a pillar, and her heart gave a little leap. She started towards him, almost skipping.

“Fancy meeting you here,” he said, a genuine smile gracing his face.

"I know!" she exclaimed. She felt like she could burst with happiness.

He took a step closer. “You look amazing.”

She felt that sensation of bubbles inside her again. “And you, sir, are looking rather dashing yourself.”

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.611
🤩0.536
de0.530
ecstatic0.527
🎉0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
😔-0.385
😥-0.379