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 cricket pitch, once a place of joy and camaraderie, now felt like a battlefield. David surveyed the team list, his gaze lingering on the names of those who had made the squad. His own name was missing. A knot formed in his chest, making it hard to swallow.

He wandered towards the edge of the field, his steps slow and hesitant. The setting sun cast elongated shadows, mimicking the darkness that seemed to have enveloped his spirit. The familiar sounds of the game, the crack of the bat, the cheers of the crowd, felt distant and muffled.

He felt a profound sense of isolation. He wanted to go home, to disappear.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322