Existing multimodal emotion and intent recognition tasks predominantly focus on classification, overlooking the underlying rationale and intrinsic connections between these states. Bridging this gap, we propose Joint Multimodal Emotion-Intent Explanation and Classification, JX4MEI, a novel task requiring the model to jointly predict emotion and intent, while generating natural language explanations for why they co-occur. To support this, we present XMEI-dataset, a large-scale benchmark of 15,461 multimodal samples spanning 7 emotion and 9 intent categories across text, audio, and visual modalities. Unlike prior works, our dataset provides fine-grained rationales for emotion, intent, and their causal interplay, curated via a rigorous pipeline involving Chain-of-Thought generation and strict human refinement to eliminate model artifacts. Furthermore, we propose XMEI-Qwen, a model equipped with a novel Language-Query Former (LQ-Former). By leveraging modality-specific captions as semantic queries, LQ-Former injects explicit semantic guidance into feature alignment, significantly enhancing reasoning capabilities. Empirical experiments demonstrate that XMEI-Qwen sets a new state-of-the-art on the JX4MEI task, outperforming competitive baselines in both prediction and explanation generation. Code: https://github.com/OrangeYeah1027/JX4MEI.