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 championship trophy gleamed under the stage lights. Sarah felt a surge of warmth spread through her. Her team had won! All those late nights, the strategic planning, the grueling practices – it had all been worth it. She was bursting with pride.

Her coworker, Tom, walked up to her, grinning. “Wow, Sarah. You really pulled it off.”

She laughed, a joyous sound. "We did! The best team!"

"I have to say, you have the same vibe as someone I know… did you ever go to Camp Greenwood?"

A shiver of excitement ran down her spine. "I did! That's amazing! You too?"

"Yep! I remember the massive slip and slide they built one year."

Emotion: triumphant

Cluster: Positive / Joy
PC1 (Valence): 3.54 Positive
PC2 (Disposition): 0.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
la0.571
triumphant0.562
🎉0.531
ecstatic0.530
Suppressed:
😞-0.503
S-0.483
😣-0.482
😰-0.457
worse-0.444