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).

He stared at the email, the words blurring through unshed tears. The screen light reflected in his eyes, making it even harder to see. He felt a hollowness in his chest, a deep ache that seemed to radiate through his entire being. He had built this up for so long.

He abandoned his morning routine of coffee and the news. The world seemed to be moving on without him, oblivious to his anguish. He pulled the covers over his head, seeking refuge in the darkness.

His phone buzzed with notifications, but he ignored them, unable to face the outside world. He wanted to be alone, to wallow in the disappointment, to escape the crushing weight of his unfulfilled dream.

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