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 house felt cavernous, the silence echoing through the empty rooms. Eleanor wandered aimlessly, the weight of the day pressing down on her. The doorbell rang, a jarring sound. It was Mr. Garcia, his usually booming laughter muted, a nervous shuffle to his feet.

“Eleanor,” he began, his voice hesitant, “I was hoping to grow some wildflowers this year, a little patch of color. My yard is a bit small. Would I be able to use a section of yours?” Eleanor’s throat constricted.

The image of blooming flowers, of vibrant hues against a backdrop of green, hit her with a fresh wave of something she was trying to avoid. She swallowed hard, a painful effort. She nodded, her face a mask, feeling a profound sense of isolation despite the presence of another human being.

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