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 silence of the house magnified the thump of Clara's heart. It was a discovery that made her flush.

She’d been tasked with clearing out her grandfather's cluttered study. And now, she held the letter in her hand. It was a draft resignation, addressed to the head of the company. A company that had defined his entire life.

Her fingers fairly danced across the paper as she smoothed it out. Her grandfather, known for his dedication, had once *wanted out*? This was unbelievable. She could feel a strange bubbling, like something was about to erupt inside her.

She sank into the chair, the letter clutched tight. It was a goldmine of information. The words were going to give her a glimpse into a hidden past.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🀩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
πŸ˜”-0.300